diff --git "a/fin_rl_dqn_v1.ipynb" "b/fin_rl_dqn_v1.ipynb" new file mode 100644--- /dev/null +++ "b/fin_rl_dqn_v1.ipynb" @@ -0,0 +1,2609 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "nwaAZRu1NTiI" + }, + "source": [ + "# DQN\n", + "\n", + "#### This version implements DQN using a custom enviroment " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "!pip install talib-binary\n", + "!pip install yfinance" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "LNXxxKojNTiL" + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "2022-12-27 12:47:16.481995: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA\n", + "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n", + "\n" + ] + } + ], + "source": [ + "import tensorflow as tf\n", + "from tensorflow.keras import layers\n", + "from tensorflow.keras.utils import to_categorical\n", + "import gym\n", + "from gym import spaces\n", + "from gym.utils import seeding\n", + "from gym import wrappers\n", + "\n", + "from tqdm.notebook import tqdm\n", + "from collections import deque\n", + "import numpy as np\n", + "import random\n", + "from matplotlib import pyplot as plt\n", + "from sklearn.preprocessing import MinMaxScaler\n", + "import joblib\n", + "import talib as ta\n", + "import yfinance as yf\n", + "import pandas as pd\n", + "\n", + "import io\n", + "import base64\n", + "from IPython.display import HTML, Video\n" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "metadata": {}, + "outputs": [], + "source": [ + "class DQN:\n", + " def __init__(self, env=None, replay_buffer_size=1000):\n", + " self.replay_buffer = deque(maxlen=replay_buffer_size)\n", + "\n", + " self.action_size = env.action_space.n\n", + "\n", + " # Hyperparameters\n", + " self.gamma = 0.95 # Discount rate\n", + " self.epsilon = 1.0 # Exploration rate\n", + " self.epsilon_min = 0.001 # Minimal exploration rate (epsilon-greedy)\n", + " self.epsilon_decay = 0.95 # Decay rate for epsilon\n", + " self.update_rate = 5 # Number of steps until updating the target network\n", + " self.batch_size = 200\n", + " self.learning_rate = 1e-4\n", + " \n", + " # Construct DQN models\n", + " self.model = self._build_model()\n", + " self.target_model = self._build_model()\n", + " self.target_model.set_weights(self.model.get_weights())\n", + " self.model.summary()\n", + " self.env = env\n", + "\n", + " self.history = None\n", + " self.scaler = None\n", + "\n", + " def _build_model(self):\n", + " model = tf.keras.Sequential()\n", + " \n", + " model.add(tf.keras.Input(shape=(4,)))\n", + " model.add(layers.Dense(256, activation = 'relu'))\n", + " model.add(layers.Dense(128, activation = 'relu'))\n", + " model.add(layers.Dense(64, activation = 'relu'))\n", + " model.add(layers.Dense(self.action_size, activation = 'linear'))\n", + " \n", + " optimizer = tf.keras.optimizers.Adam(learning_rate=self.learning_rate)\n", + " model.compile(loss='mse', optimizer=optimizer, metrics = ['mse'])\n", + " return model\n", + "\n", + "\n", + " #\n", + " # Trains the model using randomly selected experiences in the replay memory\n", + " #\n", + " def _train(self):\n", + " X, y = [], []\n", + " # state, action, reward, next_state, done \n", + " # create the targets \n", + " if self.batch_size > len(self.replay_buffer):\n", + " return\n", + " minibatch = random.sample(self.replay_buffer, self.batch_size)\n", + " mb_arr = np.array(minibatch, dtype=object)\n", + "\n", + " next_state_arr = np.stack(mb_arr[:,3])\n", + " future_qvalues = self.target_model.predict(next_state_arr, verbose=0)\n", + "\n", + " state_arr = np.stack(mb_arr[:,0])\n", + " qvalues = self.model.predict(state_arr, verbose=0)\n", + "\n", + " for index, (state, action, reward, next_state, done) in enumerate(minibatch):\n", + " if done == True:\n", + " q_target = reward\n", + " else:\n", + " q_target = reward + self.gamma * np.max(future_qvalues[index])\n", + "\n", + " q_curr = qvalues[index]\n", + " q_curr[action] = q_target \n", + " X.append(state)\n", + " y.append(q_curr)\n", + "\n", + " # Perform gradient step\n", + " X, y = np.array(X), np.array(y)\n", + " self.history = self.model.fit(X, y, batch_size = self.batch_size, shuffle = False, verbose=0)\n", + " # history = self.model.fit(X, y, epochs=1, verbose=0)\n", + " # print(f\"Loss: {history.history['loss']} \")\n", + "\n", + "\n", + " def learn(self, total_steps=None):\n", + " current_episode = 0\n", + " total_reward = 0\n", + " rewards = [0]\n", + " current_step = 0\n", + " while current_step < total_steps:\n", + " current_episode += 1\n", + " state = self.env.reset()\n", + " total_reward = 0\n", + " done = False\n", + " while done != True:\n", + " current_step +=1\n", + " # e-greedy\n", + " if np.random.random() > (1 - self.epsilon):\n", + " action = np.random.randint(self.action_size)\n", + " else:\n", + " model_predict = self.model.predict(np.array([state]), verbose=0)\n", + " action = np.argmax(model_predict)\n", + "\n", + " # step\n", + " next_state, reward, done, info = self.env.step(action)\n", + " total_reward += reward\n", + "\n", + " # add to buffer\n", + " self.replay_buffer.append((state, action, reward, next_state, done))\n", + "\n", + " if current_step>10 and current_step % self.update_rate == 0:\n", + " print(f\"epsilon:{self.epsilon} step:{current_step} episode:{current_episode} last_score {rewards[-1]} Profit {info['total_profit']} Loss {self.history.history['loss']}\")\n", + " self._train()\n", + " # update target\n", + " self.target_model.set_weights(self.model.get_weights())\n", + " \n", + " state = next_state\n", + "\n", + " # update epsilon \n", + " if current_step % 20 == 0:\n", + " if self.epsilon > self.epsilon_min:\n", + " self.epsilon *= self.epsilon_decay\n", + "\n", + " rewards.append(total_reward)\n", + "\n", + " #\n", + " # Loads a saved model\n", + " #\n", + " def load(self, name):\n", + " self.model = tf.keras.models.load_model(name)\n", + " # self.scaler = joblib.load(name+\".scaler\") \n", + "\n", + " #\n", + " # Saves parameters of a trained model\n", + " #\n", + " def save(self, name):\n", + " self.model.save(name)\n", + " # joblib.dump(self.scaler, name+\".scaler\") \n", + "\n", + " def play(self, state):\n", + " # state = self._get_scaled_state(state)\n", + " return np.argmax(self.model.predict(np.array([state]), verbose=0)[0])" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": {}, + "outputs": [], + "source": [ + "from enum import Enum\n", + "class Actions(Enum):\n", + " Sell = 0\n", + " Buy = 1\n", + " Do_nothing = 2\n", + "\n", + "class CustTradingEnv(gym.Env):\n", + "\n", + " def __init__(self, df, max_steps=0, seed=8, random_start=True, scaler=None):\n", + " self.seed(seed=seed)\n", + " self.df = df\n", + " if scaler is None:\n", + " self.scaler = MinMaxScaler()\n", + " else:\n", + " self.scaler = scaler\n", + " self.prices, self.signal_features = self._process_data()\n", + "\n", + " # spaces\n", + " self.action_space = spaces.Discrete(3)\n", + " self.observation_space = spaces.Box(low=0, high=1, shape=(1,) , dtype=np.float64)\n", + "\n", + " # episode\n", + " self._start_tick = 0\n", + " self._end_tick = 0\n", + " self._done = None\n", + " self._current_tick = None\n", + " self._last_trade_tick = None\n", + " self._position = None\n", + " self._position_history = None\n", + " self._total_reward = None\n", + " self._total_profit = None\n", + " self._first_rendering = None\n", + " self.history = None\n", + " self._max_steps = max_steps\n", + " self._start_episode_tick = None\n", + " self._trade_history = None\n", + " self._random_start = random_start\n", + "\n", + "\n", + " def reset(self):\n", + " self._done = False\n", + " if self._random_start:\n", + " self._start_episode_tick = np.random.randint(1,high=len(self.df)- self._max_steps )\n", + " self._end_tick = self._start_episode_tick + self._max_steps\n", + " else:\n", + " self._start_episode_tick = 1\n", + " self._end_tick = len(self.df)-1\n", + "\n", + " self._current_tick = self._start_episode_tick\n", + " self._last_trade_tick = self._current_tick - 1\n", + " self._position = 0\n", + " self._position_history = []\n", + " # self._position_history = (self.window_size * [None]) + [self._position]\n", + " self._total_reward = 0.\n", + " self._total_profit = 0.\n", + " self._trade_history = []\n", + " self.history = {}\n", + " return self._get_observation()\n", + "\n", + "\n", + " def step(self, action):\n", + " self._done = False\n", + " self._current_tick += 1\n", + "\n", + " if self._current_tick == self._end_tick:\n", + " self._done = True\n", + "\n", + " step_reward = self._calculate_reward(action)\n", + " self._total_reward += step_reward\n", + "\n", + " observation = self._get_observation()\n", + " info = dict(\n", + " total_reward = self._total_reward,\n", + " total_profit = self._total_profit,\n", + " position = self._position,\n", + " action = action\n", + " )\n", + " self._update_history(info)\n", + "\n", + " return observation, step_reward, self._done, info\n", + "\n", + " def seed(self, seed=None):\n", + " self.np_random, seed = seeding.np_random(seed)\n", + " return [seed]\n", + " \n", + " def _get_observation(self):\n", + " return self.signal_features[self._current_tick]\n", + "\n", + " def _update_history(self, info):\n", + " if not self.history:\n", + " self.history = {key: [] for key in info.keys()}\n", + "\n", + " for key, value in info.items():\n", + " self.history[key].append(value)\n", + "\n", + "\n", + " def render(self, mode='human'):\n", + " window_ticks = np.arange(len(self._position_history))\n", + " prices = self.prices[self._start_episode_tick:self._end_tick+1]\n", + " plt.plot(prices)\n", + "\n", + " open_buy = []\n", + " close_buy = []\n", + " open_sell = []\n", + " close_sell = []\n", + " do_nothing = []\n", + "\n", + " for i, tick in enumerate(window_ticks):\n", + " if self._position_history[i] == 1:\n", + " open_buy.append(tick)\n", + " elif self._position_history[i] == 2 :\n", + " close_buy.append(tick)\n", + " elif self._position_history[i] == 3 :\n", + " open_sell.append(tick)\n", + " elif self._position_history[i] == 4 :\n", + " close_sell.append(tick)\n", + " elif self._position_history[i] == 0 :\n", + " do_nothing.append(tick)\n", + "\n", + " plt.plot(open_buy, prices[open_buy], 'go', marker=\"^\")\n", + " plt.plot(close_buy, prices[close_buy], 'go', marker=\"v\")\n", + " plt.plot(open_sell, prices[open_sell], 'ro', marker=\"v\")\n", + " plt.plot(close_sell, prices[close_sell], 'ro', marker=\"^\")\n", + " \n", + " plt.plot(do_nothing, prices[do_nothing], 'yo')\n", + "\n", + " plt.suptitle(\n", + " \"Total Reward: %.6f\" % self._total_reward + ' ~ ' +\n", + " \"Total Profit: %.6f\" % self._total_profit\n", + " )\n", + "\n", + " def _calculate_reward(self, action):\n", + " step_reward = 0\n", + "\n", + " current_price = self.prices[self._current_tick]\n", + " last_price = self.prices[self._current_tick - 1]\n", + " price_diff = current_price - last_price\n", + "\n", + " penalty = -1 * last_price * 0.01\n", + " # OPEN BUY - 1\n", + " if action == Actions.Buy.value and self._position == 0:\n", + " self._position = 1\n", + " step_reward += price_diff\n", + " self._last_trade_tick = self._current_tick - 1\n", + " self._position_history.append(1)\n", + "\n", + " elif action == Actions.Buy.value and self._position > 0:\n", + " step_reward += penalty\n", + " self._position_history.append(-1)\n", + " # CLOSE SELL - 4\n", + " elif action == Actions.Buy.value and self._position < 0:\n", + " self._position = 0\n", + " step_reward += -1 * (self.prices[self._current_tick -1] - self.prices[self._last_trade_tick]) \n", + " self._total_profit += step_reward\n", + " self._position_history.append(4)\n", + " self._trade_history.append(step_reward)\n", + "\n", + " # OPEN SELL - 3\n", + " elif action == Actions.Sell.value and self._position == 0:\n", + " self._position = -1\n", + " step_reward += -1 * price_diff\n", + " self._last_trade_tick = self._current_tick - 1\n", + " self._position_history.append(3)\n", + " # CLOSE BUY - 2\n", + " elif action == Actions.Sell.value and self._position > 0:\n", + " self._position = 0\n", + " step_reward += self.prices[self._current_tick -1] - self.prices[self._last_trade_tick] \n", + " self._total_profit += step_reward\n", + " self._position_history.append(2)\n", + " self._trade_history.append(step_reward)\n", + " elif action == Actions.Sell.value and self._position < 0:\n", + " step_reward += penalty\n", + " self._position_history.append(-1)\n", + "\n", + " # DO NOTHING - 0\n", + " elif action == Actions.Do_nothing.value and self._position > 0:\n", + " step_reward += price_diff\n", + " self._position_history.append(0)\n", + " elif action == Actions.Do_nothing.value and self._position < 0:\n", + " step_reward += -1 * price_diff\n", + " self._position_history.append(0)\n", + " elif action == Actions.Do_nothing.value and self._position == 0:\n", + " step_reward += -1 * abs(price_diff)\n", + " self._position_history.append(0)\n", + "\n", + " return step_reward\n", + "\n", + " def get_scaler(self):\n", + " return self.scaler\n", + "\n", + " def set_scaler(self, scaler):\n", + " self.scaler = scaler\n", + " \n", + " def _process_data(self):\n", + " timeperiod = 14\n", + " self.df = self.df.copy()\n", + " \n", + " self.df['mfi_r'] = ta.MFI(self.df['High'], self.df['Low'], self.df['Close'],self.df['Volume'], timeperiod=timeperiod)\n", + " _, self.df['stoch_d_r'] = ta.STOCH(self.df['High'], self.df['Low'], self.df['Close'], fastk_period=5, slowk_period=3, slowk_matype=0, slowd_period=3, slowd_matype=0)\n", + " self.df['adx_r'] = ta.ADX(self.df['High'], self.df['Low'], self.df['Close'], timeperiod=timeperiod)\n", + " self.df['p_di'] = ta.PLUS_DI(self.df['High'], self.df['Low'], self.df['Close'], timeperiod=timeperiod)\n", + " self.df['m_di'] = ta.MINUS_DI(self.df['High'], self.df['Low'], self.df['Close'], timeperiod=timeperiod)\n", + " self.df['di'] = np.where( self.df['p_di'] > self.df['m_di'], 1, 0)\n", + "\n", + " self.df = self.df.dropna()\n", + " # self.df['di_s']=self.df['di']\n", + " # self.df['mfi_s']=self.df['mfi_r']\n", + " # self.df['stoch_d_s']=self.df['stoch_d_r']\n", + " # self.df['adx_s']=self.df['adx_r']\n", + "\n", + " self.df[['di_s','mfi_s','stoch_d_s','adx_s']] = self.scaler.fit_transform(self.df[['di','mfi_r','stoch_d_r','adx_r']])\n", + "\n", + " def f1(row):\n", + " row['state'] = [row['di_s'], row['mfi_s'], row['stoch_d_s'], row['adx_s']]\n", + " return row\n", + "\n", + " self.df = self.df.apply(f1, axis=1 )\n", + "\n", + " prices = self.df.loc[:, 'Close'].to_numpy()\n", + " # print(self.df.head(30))\n", + "\n", + " signal_features = np.stack(self.df.loc[:, 'state'].to_numpy())\n", + "\n", + " return prices, signal_features" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "3024\n", + "1875\n" + ] + } + ], + "source": [ + "# Get data\n", + "eth_usd = yf.Ticker(\"ETH-USD\")\n", + "eth = eth_usd.history(period=\"max\")\n", + "\n", + "btc_usd = yf.Ticker(\"BTC-USD\")\n", + "btc = btc_usd.history(period=\"max\")\n", + "print(len(btc))\n", + "print(len(eth))\n", + "\n", + "btc_train = eth[-3015:-200]\n", + "# btc_test = eth[-200:]\n", + "eth_train = eth[-1864:-200]\n", + "eth_test = eth[-200:]\n", + "# len(eth_train)" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Model: \"sequential_12\"\n", + "_________________________________________________________________\n", + " Layer (type) Output Shape Param # \n", + "=================================================================\n", + " dense_48 (Dense) (None, 256) 1280 \n", + " \n", + " dense_49 (Dense) (None, 128) 32896 \n", + " \n", + " dense_50 (Dense) (None, 64) 8256 \n", + " \n", + " dense_51 (Dense) (None, 3) 195 \n", + " \n", + "=================================================================\n", + "Total params: 42,627\n", + "Trainable params: 42,627\n", + "Non-trainable params: 0\n", + "_________________________________________________________________\n", + "epsilon:1.0 step:15 episode:1 last_score 0 Profit -137.1817626953125 Loss None\n", + "epsilon:1.0 step:20 episode:1 last_score 0 Profit -134.0233154296875 Loss None\n", + "epsilon:0.95 step:25 episode:2 last_score -966.53455078125 Profit -3.1496124267578125 Loss None\n", + "epsilon:0.95 step:30 episode:2 last_score -966.53455078125 Profit 2.0914306640625 Loss None\n", + "epsilon:0.95 step:35 episode:2 last_score -966.53455078125 Profit 5.436676025390625 Loss None\n", + "epsilon:0.95 step:40 episode:2 last_score -966.53455078125 Profit 7.9377899169921875 Loss None\n", + "epsilon:0.9025 step:45 episode:3 last_score 5.3660481262207025 Profit 395.0810546875 Loss None\n", + "epsilon:0.9025 step:50 episode:3 last_score 5.3660481262207025 Profit 505.3583984375 Loss None\n", + "epsilon:0.9025 step:55 episode:3 last_score 5.3660481262207025 Profit 590.62158203125 Loss None\n", + "epsilon:0.9025 step:60 episode:3 last_score 5.3660481262207025 Profit 453.9375 Loss None\n", + "epsilon:0.8573749999999999 step:65 episode:4 last_score 1016.5273071289062 Profit 0.0 Loss None\n", + "epsilon:0.8573749999999999 step:70 episode:4 last_score 1016.5273071289062 Profit -9.22235107421875 Loss None\n", + "epsilon:0.8573749999999999 step:75 episode:4 last_score 1016.5273071289062 Profit -5.6952667236328125 Loss None\n", + "epsilon:0.8573749999999999 step:80 episode:4 last_score 1016.5273071289062 Profit -7.02288818359375 Loss None\n", + "epsilon:0.8145062499999999 step:85 episode:5 last_score -23.508456420898437 Profit 0.0 Loss None\n", + "epsilon:0.8145062499999999 step:90 episode:5 last_score -23.508456420898437 Profit 139.99359130859375 Loss None\n", + "epsilon:0.8145062499999999 step:95 episode:5 last_score -23.508456420898437 Profit 139.99359130859375 Loss None\n", + "epsilon:0.8145062499999999 step:100 episode:5 last_score -23.508456420898437 Profit 162.66473388671875 Loss None\n", + "epsilon:0.7737809374999999 step:105 episode:6 last_score 243.0426364135742 Profit 2.303466796875 Loss None\n", + "epsilon:0.7737809374999999 step:110 episode:6 last_score 243.0426364135742 Profit 12.927566528320312 Loss None\n", + "epsilon:0.7737809374999999 step:115 episode:6 last_score 243.0426364135742 Profit 5.7935028076171875 Loss None\n", + "epsilon:0.7737809374999999 step:120 episode:6 last_score 243.0426364135742 Profit 10.906723022460938 Loss None\n", + "epsilon:0.7350918906249998 step:125 episode:7 last_score 21.333234558105467 Profit 27.886993408203125 Loss None\n", + "epsilon:0.7350918906249998 step:130 episode:7 last_score 21.333234558105467 Profit 29.575958251953125 Loss None\n", + "epsilon:0.7350918906249998 step:135 episode:7 last_score 21.333234558105467 Profit -22.57904052734375 Loss None\n", + "epsilon:0.7350918906249998 step:140 episode:7 last_score 21.333234558105467 Profit -22.57904052734375 Loss None\n", + "epsilon:0.6983372960937497 step:145 episode:8 last_score -153.12630615234374 Profit 0.0 Loss None\n", + "epsilon:0.6983372960937497 step:150 episode:8 last_score -153.12630615234374 Profit 0.0 Loss None\n", + "epsilon:0.6983372960937497 step:155 episode:8 last_score -153.12630615234374 Profit -72.052490234375 Loss None\n", + "epsilon:0.6983372960937497 step:160 episode:8 last_score -153.12630615234374 Profit -72.052490234375 Loss None\n", + "epsilon:0.6634204312890623 step:165 episode:9 last_score -1187.3944995117188 Profit 488.588623046875 Loss None\n", + "epsilon:0.6634204312890623 step:170 episode:9 last_score -1187.3944995117188 Profit 1267.70751953125 Loss None\n", + "epsilon:0.6634204312890623 step:175 episode:9 last_score -1187.3944995117188 Profit 1267.70751953125 Loss None\n", + "epsilon:0.6634204312890623 step:180 episode:9 last_score -1187.3944995117188 Profit 1046.099365234375 Loss None\n", + "epsilon:0.6302494097246091 step:185 episode:10 last_score 503.37905273437514 Profit 0.15612030029296875 Loss None\n", + "epsilon:0.6302494097246091 step:190 episode:10 last_score 503.37905273437514 Profit 14.161880493164062 Loss None\n", + "epsilon:0.6302494097246091 step:195 episode:10 last_score 503.37905273437514 Profit 14.161880493164062 Loss None\n", + "epsilon:0.6302494097246091 step:200 episode:10 last_score 503.37905273437514 Profit 14.161880493164062 Loss None\n", + "epsilon:0.5987369392383786 step:205 episode:11 last_score 30.34539779663086 Profit 0.0 Loss [4362.67333984375]\n", + "epsilon:0.5987369392383786 step:210 episode:11 last_score 30.34539779663086 Profit 0.7960052490234375 Loss [4195.63623046875]\n", + "epsilon:0.5987369392383786 step:215 episode:11 last_score 30.34539779663086 Profit 0.7960052490234375 Loss [3907.09130859375]\n", + "epsilon:0.5987369392383786 step:220 episode:11 last_score 30.34539779663086 Profit 0.7960052490234375 Loss [3958.101318359375]\n", + "epsilon:0.5688000922764596 step:225 episode:12 last_score -45.63256057739258 Profit 0.0 Loss [4289.54296875]\n", + "epsilon:0.5688000922764596 step:230 episode:12 last_score -45.63256057739258 Profit 331.529052734375 Loss [4067.746826171875]\n", + "epsilon:0.5688000922764596 step:235 episode:12 last_score -45.63256057739258 Profit 407.494140625 Loss [3949.726806640625]\n", + "epsilon:0.5688000922764596 step:240 episode:12 last_score -45.63256057739258 Profit 427.132568359375 Loss [4019.71875]\n", + "epsilon:0.5403600876626365 step:245 episode:13 last_score 348.78031250000004 Profit 0.0 Loss [4609.63623046875]\n", + "epsilon:0.5403600876626365 step:250 episode:13 last_score 348.78031250000004 Profit 299.311279296875 Loss [4688.31201171875]\n", + "epsilon:0.5403600876626365 step:255 episode:13 last_score 348.78031250000004 Profit 260.854248046875 Loss [4593.49072265625]\n", + "epsilon:0.5403600876626365 step:260 episode:13 last_score 348.78031250000004 Profit 260.854248046875 Loss [4009.8798828125]\n", + "epsilon:0.5133420832795047 step:265 episode:14 last_score -170.15158203125003 Profit -3.1409912109375 Loss [4480.7392578125]\n", + "epsilon:0.5133420832795047 step:270 episode:14 last_score -170.15158203125003 Profit -3.1409912109375 Loss [4348.64453125]\n", + "epsilon:0.5133420832795047 step:275 episode:14 last_score -170.15158203125003 Profit 260.945068359375 Loss [3808.439453125]\n", + "epsilon:0.5133420832795047 step:280 episode:14 last_score -170.15158203125003 Profit 260.945068359375 Loss [3678.453857421875]\n", + "epsilon:0.48767497911552943 step:285 episode:15 last_score -93.04297119140624 Profit 13.091461181640625 Loss [3825.1748046875]\n", + "epsilon:0.48767497911552943 step:290 episode:15 last_score -93.04297119140624 Profit -8.3914794921875 Loss [3902.41552734375]\n", + "epsilon:0.48767497911552943 step:295 episode:15 last_score -93.04297119140624 Profit 8.897369384765625 Loss [4884.228515625]\n", + "epsilon:0.48767497911552943 step:300 episode:15 last_score -93.04297119140624 Profit 58.30517578125 Loss [3660.840576171875]\n", + "epsilon:0.46329123015975293 step:305 episode:16 last_score 61.346580505371094 Profit 140.1982421875 Loss [4400.73681640625]\n", + "epsilon:0.46329123015975293 step:310 episode:16 last_score 61.346580505371094 Profit 140.1982421875 Loss [3377.720947265625]\n", + "epsilon:0.46329123015975293 step:315 episode:16 last_score 61.346580505371094 Profit -428.253662109375 Loss [4492.3583984375]\n", + "epsilon:0.46329123015975293 step:320 episode:16 last_score 61.346580505371094 Profit -669.288818359375 Loss [3565.09521484375]\n", + "epsilon:0.44012666865176525 step:325 episode:17 last_score -1139.8885424804687 Profit -6.1264190673828125 Loss [4786.02001953125]\n", + "epsilon:0.44012666865176525 step:330 episode:17 last_score -1139.8885424804687 Profit -7.723602294921875 Loss [3610.43115234375]\n", + "epsilon:0.44012666865176525 step:335 episode:17 last_score -1139.8885424804687 Profit -4.08587646484375 Loss [4301.66259765625]\n", + "epsilon:0.44012666865176525 step:340 episode:17 last_score -1139.8885424804687 Profit -1.4617767333984375 Loss [4027.2431640625]\n", + "epsilon:0.41812033521917696 step:345 episode:18 last_score -19.616720886230468 Profit 19.812286376953125 Loss [4600.27197265625]\n", + "epsilon:0.41812033521917696 step:350 episode:18 last_score -19.616720886230468 Profit 19.812286376953125 Loss [4773.404296875]\n", + "epsilon:0.41812033521917696 step:355 episode:18 last_score -19.616720886230468 Profit 33.24092102050781 Loss [4860.693359375]\n", + "epsilon:0.41812033521917696 step:360 episode:18 last_score -19.616720886230468 Profit 40.43046569824219 Loss [2285.71875]\n", + "epsilon:0.3972143184582181 step:365 episode:19 last_score 56.070802764892576 Profit -140.60009765625 Loss [2982.994140625]\n", + "epsilon:0.3972143184582181 step:370 episode:19 last_score 56.070802764892576 Profit 187.0699462890625 Loss [4133.31201171875]\n", + "epsilon:0.3972143184582181 step:375 episode:19 last_score 56.070802764892576 Profit 187.0699462890625 Loss [2689.860595703125]\n", + "epsilon:0.3972143184582181 step:380 episode:19 last_score 56.070802764892576 Profit 187.0699462890625 Loss [2855.096923828125]\n", + "epsilon:0.37735360253530714 step:385 episode:20 last_score 160.3465661621094 Profit 105.570068359375 Loss [4217.525390625]\n", + "epsilon:0.37735360253530714 step:390 episode:20 last_score 160.3465661621094 Profit 105.570068359375 Loss [3157.32373046875]\n", + "epsilon:0.37735360253530714 step:395 episode:20 last_score 160.3465661621094 Profit 105.570068359375 Loss [3292.226318359375]\n", + "epsilon:0.37735360253530714 step:400 episode:20 last_score 160.3465661621094 Profit 105.570068359375 Loss [3208.161865234375]\n", + "epsilon:0.35848592240854177 step:405 episode:21 last_score 137.29813598632816 Profit 0.0 Loss [3514.228759765625]\n", + "epsilon:0.35848592240854177 step:410 episode:21 last_score 137.29813598632816 Profit 0.0 Loss [3688.78564453125]\n", + "epsilon:0.35848592240854177 step:415 episode:21 last_score 137.29813598632816 Profit 0.0 Loss [1835.838134765625]\n", + "epsilon:0.35848592240854177 step:420 episode:21 last_score 137.29813598632816 Profit 0.0 Loss [4517.2626953125]\n", + "epsilon:0.34056162628811465 step:425 episode:22 last_score -20.198392639160158 Profit 0.0 Loss [2953.627197265625]\n", + "epsilon:0.34056162628811465 step:430 episode:22 last_score -20.198392639160158 Profit 0.0 Loss [3014.7060546875]\n", + "epsilon:0.34056162628811465 step:435 episode:22 last_score -20.198392639160158 Profit 117.76898193359375 Loss [5063.49658203125]\n", + "epsilon:0.34056162628811465 step:440 episode:22 last_score -20.198392639160158 Profit 117.76898193359375 Loss [4256.8486328125]\n", + "epsilon:0.3235335449737089 step:445 episode:23 last_score 87.37741760253905 Profit 0.0 Loss [3465.94384765625]\n", + "epsilon:0.3235335449737089 step:450 episode:23 last_score 87.37741760253905 Profit 0.0 Loss [4514.01318359375]\n", + "epsilon:0.3235335449737089 step:455 episode:23 last_score 87.37741760253905 Profit 202.331298828125 Loss [3099.851318359375]\n", + "epsilon:0.3235335449737089 step:460 episode:23 last_score 87.37741760253905 Profit 693.70263671875 Loss [5450.25634765625]\n", + "epsilon:0.30735686772502346 step:465 episode:24 last_score 898.2041186523438 Profit 0.0 Loss [4375.01611328125]\n", + "epsilon:0.30735686772502346 step:470 episode:24 last_score 898.2041186523438 Profit 129.0419921875 Loss [3255.439453125]\n", + "epsilon:0.30735686772502346 step:475 episode:24 last_score 898.2041186523438 Profit 149.61895751953125 Loss [3239.171142578125]\n", + "epsilon:0.30735686772502346 step:480 episode:24 last_score 898.2041186523438 Profit 149.61895751953125 Loss [3780.631591796875]\n", + "epsilon:0.2919890243387723 step:485 episode:25 last_score 216.11007293701172 Profit 0.0 Loss [4603.767578125]\n", + "epsilon:0.2919890243387723 step:490 episode:25 last_score 216.11007293701172 Profit 0.0 Loss [3428.779296875]\n", + "epsilon:0.2919890243387723 step:495 episode:25 last_score 216.11007293701172 Profit 0.0 Loss [3780.596923828125]\n", + "epsilon:0.2919890243387723 step:500 episode:25 last_score 216.11007293701172 Profit 0.0 Loss [2680.195068359375]\n", + "epsilon:0.27738957312183365 step:505 episode:26 last_score -729.5176782226563 Profit 0.0 Loss [6188.32958984375]\n", + "epsilon:0.27738957312183365 step:510 episode:26 last_score -729.5176782226563 Profit 0.0 Loss [1996.4854736328125]\n", + "epsilon:0.27738957312183365 step:515 episode:26 last_score -729.5176782226563 Profit -5.0469970703125 Loss [3432.969970703125]\n", + "epsilon:0.27738957312183365 step:520 episode:26 last_score -729.5176782226563 Profit -5.0469970703125 Loss [3457.7666015625]\n", + "epsilon:0.263520094465742 step:525 episode:27 last_score -25.652086181640627 Profit 0.0 Loss [3444.86279296875]\n", + "epsilon:0.263520094465742 step:530 episode:27 last_score -25.652086181640627 Profit 0.0 Loss [3893.00244140625]\n", + "epsilon:0.263520094465742 step:535 episode:27 last_score -25.652086181640627 Profit 0.0 Loss [3572.597412109375]\n", + "epsilon:0.263520094465742 step:540 episode:27 last_score -25.652086181640627 Profit 0.0 Loss [2144.427734375]\n", + "epsilon:0.25034408974245487 step:545 episode:28 last_score -542.6016870117188 Profit 7.601898193359375 Loss [3809.282470703125]\n", + "epsilon:0.25034408974245487 step:550 episode:28 last_score -542.6016870117188 Profit 7.601898193359375 Loss [5816.064453125]\n", + "epsilon:0.25034408974245487 step:555 episode:28 last_score -542.6016870117188 Profit 7.601898193359375 Loss [3378.37939453125]\n", + "epsilon:0.25034408974245487 step:560 episode:28 last_score -542.6016870117188 Profit 7.601898193359375 Loss [2052.171630859375]\n", + "epsilon:0.2378268852553321 step:565 episode:29 last_score -15.533706970214848 Profit 0.0 Loss [1675.9368896484375]\n", + "epsilon:0.2378268852553321 step:570 episode:29 last_score -15.533706970214848 Profit 0.0 Loss [5293.0849609375]\n", + "epsilon:0.2378268852553321 step:575 episode:29 last_score -15.533706970214848 Profit -28.77593994140625 Loss [3384.843994140625]\n", + "epsilon:0.2378268852553321 step:580 episode:29 last_score -15.533706970214848 Profit -28.77593994140625 Loss [3564.8857421875]\n", + "epsilon:0.2259355409925655 step:585 episode:30 last_score -91.8448208618164 Profit 0.0 Loss [4261.51953125]\n", + "epsilon:0.2259355409925655 step:590 episode:30 last_score -91.8448208618164 Profit 0.0 Loss [3443.748779296875]\n", + "epsilon:0.2259355409925655 step:595 episode:30 last_score -91.8448208618164 Profit -30.91973876953125 Loss [3730.149169921875]\n", + "epsilon:0.2259355409925655 step:600 episode:30 last_score -91.8448208618164 Profit -30.91973876953125 Loss [4064.742431640625]\n", + "epsilon:0.2146387639429372 step:605 episode:31 last_score -102.62495391845702 Profit 210.5267333984375 Loss [1576.1640625]\n", + "epsilon:0.2146387639429372 step:610 episode:31 last_score -102.62495391845702 Profit 210.5267333984375 Loss [4938.599609375]\n", + "epsilon:0.2146387639429372 step:615 episode:31 last_score -102.62495391845702 Profit 48.3939208984375 Loss [2171.616455078125]\n", + "epsilon:0.2146387639429372 step:620 episode:31 last_score -102.62495391845702 Profit -153.1376953125 Loss [6264.86865234375]\n", + "epsilon:0.20390682574579033 step:625 episode:32 last_score -405.56800170898435 Profit 58.914794921875 Loss [2354.902587890625]\n", + "epsilon:0.20390682574579033 step:630 episode:32 last_score -405.56800170898435 Profit 58.914794921875 Loss [4002.933837890625]\n", + "epsilon:0.20390682574579033 step:635 episode:32 last_score -405.56800170898435 Profit 66.1982421875 Loss [4336.47265625]\n", + "epsilon:0.20390682574579033 step:640 episode:32 last_score -405.56800170898435 Profit 66.1982421875 Loss [2578.630126953125]\n", + "epsilon:0.1937114844585008 step:645 episode:33 last_score -247.35352050781253 Profit -4.56085205078125 Loss [3247.084716796875]\n", + "epsilon:0.1937114844585008 step:650 episode:33 last_score -247.35352050781253 Profit -4.56085205078125 Loss [3147.260009765625]\n", + "epsilon:0.1937114844585008 step:655 episode:33 last_score -247.35352050781253 Profit -4.56085205078125 Loss [3366.86962890625]\n", + "epsilon:0.1937114844585008 step:660 episode:33 last_score -247.35352050781253 Profit -44.85716247558594 Loss [2332.83251953125]\n", + "epsilon:0.18402591023557577 step:665 episode:34 last_score -68.3705542755127 Profit 209.1220703125 Loss [1609.1522216796875]\n", + "epsilon:0.18402591023557577 step:670 episode:34 last_score -68.3705542755127 Profit 599.137451171875 Loss [4007.978515625]\n", + "epsilon:0.18402591023557577 step:675 episode:34 last_score -68.3705542755127 Profit 599.137451171875 Loss [3607.3974609375]\n", + "epsilon:0.18402591023557577 step:680 episode:34 last_score -68.3705542755127 Profit 472.14208984375 Loss [1976.3187255859375]\n", + "epsilon:0.17482461472379698 step:685 episode:35 last_score 381.3840698242186 Profit 0.0 Loss [4067.682861328125]\n", + "epsilon:0.17482461472379698 step:690 episode:35 last_score 381.3840698242186 Profit 0.0 Loss [2650.139404296875]\n", + "epsilon:0.17482461472379698 step:695 episode:35 last_score 381.3840698242186 Profit 0.0 Loss [4366.64453125]\n", + "epsilon:0.17482461472379698 step:700 episode:35 last_score 381.3840698242186 Profit -65.15119934082031 Loss [5081.16845703125]\n", + "epsilon:0.16608338398760714 step:705 episode:36 last_score -65.80480194091797 Profit 36.82756042480469 Loss [1805.8028564453125]\n", + "epsilon:0.16608338398760714 step:710 episode:36 last_score -65.80480194091797 Profit 36.82756042480469 Loss [2530.76904296875]\n", + "epsilon:0.16608338398760714 step:715 episode:36 last_score -65.80480194091797 Profit 23.408889770507812 Loss [2473.1845703125]\n", + "epsilon:0.16608338398760714 step:720 episode:36 last_score -65.80480194091797 Profit 71.48277282714844 Loss [2257.916259765625]\n", + "epsilon:0.15777921478822676 step:725 episode:37 last_score 75.71849792480468 Profit 0.0 Loss [2480.3173828125]\n", + "epsilon:0.15777921478822676 step:730 episode:37 last_score 75.71849792480468 Profit -4.280975341796875 Loss [4497.53564453125]\n", + "epsilon:0.15777921478822676 step:735 episode:37 last_score 75.71849792480468 Profit 8.155136108398438 Loss [3536.57373046875]\n", + "epsilon:0.15777921478822676 step:740 episode:37 last_score 75.71849792480468 Profit 8.155136108398438 Loss [3266.484375]\n", + "epsilon:0.14989025404881542 step:745 episode:38 last_score -33.209679718017576 Profit 0.0 Loss [4252.02734375]\n", + "epsilon:0.14989025404881542 step:750 episode:38 last_score -33.209679718017576 Profit -328.4173583984375 Loss [2315.593994140625]\n", + "epsilon:0.14989025404881542 step:755 episode:38 last_score -33.209679718017576 Profit -178.9366455078125 Loss [1225.818115234375]\n", + "epsilon:0.14989025404881542 step:760 episode:38 last_score -33.209679718017576 Profit -178.9366455078125 Loss [4428.5712890625]\n", + "epsilon:0.14239574134637464 step:765 episode:39 last_score -254.1115942382812 Profit 0.0 Loss [1838.9447021484375]\n", + "epsilon:0.14239574134637464 step:770 episode:39 last_score -254.1115942382812 Profit -15.893402099609375 Loss [1813.5540771484375]\n", + "epsilon:0.14239574134637464 step:775 episode:39 last_score -254.1115942382812 Profit -9.3419189453125 Loss [2652.793701171875]\n", + "epsilon:0.14239574134637464 step:780 episode:39 last_score -254.1115942382812 Profit 10.0096435546875 Loss [4012.22998046875]\n", + "epsilon:0.1352759542790559 step:785 episode:40 last_score -62.33170318603513 Profit -15.102447509765625 Loss [2931.446044921875]\n", + "epsilon:0.1352759542790559 step:790 episode:40 last_score -62.33170318603513 Profit -59.6854248046875 Loss [1800.0244140625]\n", + "epsilon:0.1352759542790559 step:795 episode:40 last_score -62.33170318603513 Profit -116.90449523925781 Loss [1974.5184326171875]\n", + "epsilon:0.1352759542790559 step:800 episode:40 last_score -62.33170318603513 Profit -116.90449523925781 Loss [3162.300537109375]\n", + "epsilon:0.1285121565651031 step:805 episode:41 last_score -197.03491638183596 Profit -191.53271484375 Loss [3336.662109375]\n", + "epsilon:0.1285121565651031 step:810 episode:41 last_score -197.03491638183596 Profit -369.09765625 Loss [1585.4715576171875]\n", + "epsilon:0.1285121565651031 step:815 episode:41 last_score -197.03491638183596 Profit -369.09765625 Loss [3588.902587890625]\n", + "epsilon:0.1285121565651031 step:820 episode:41 last_score -197.03491638183596 Profit -369.09765625 Loss [2425.222900390625]\n", + "epsilon:0.12208654873684793 step:825 episode:42 last_score -1243.8220214843752 Profit 0.0 Loss [2943.187255859375]\n", + "epsilon:0.12208654873684793 step:830 episode:42 last_score -1243.8220214843752 Profit 0.0 Loss [2582.636474609375]\n", + "epsilon:0.12208654873684793 step:835 episode:42 last_score -1243.8220214843752 Profit 0.0 Loss [2340.6416015625]\n", + "epsilon:0.12208654873684793 step:840 episode:42 last_score -1243.8220214843752 Profit 0.0 Loss [2789.349609375]\n", + "epsilon:0.11598222130000553 step:845 episode:43 last_score -703.6830615234376 Profit 2.4290924072265625 Loss [2568.064697265625]\n", + "epsilon:0.11598222130000553 step:850 episode:43 last_score -703.6830615234376 Profit 2.4290924072265625 Loss [3174.047119140625]\n", + "epsilon:0.11598222130000553 step:855 episode:43 last_score -703.6830615234376 Profit 2.4290924072265625 Loss [2865.23876953125]\n", + "epsilon:0.11598222130000553 step:860 episode:43 last_score -703.6830615234376 Profit 2.4290924072265625 Loss [2672.01806640625]\n", + "epsilon:0.11018311023500525 step:865 episode:44 last_score -23.702634887695318 Profit 0.0 Loss [2743.427490234375]\n", + "epsilon:0.11018311023500525 step:870 episode:44 last_score -23.702634887695318 Profit 0.0 Loss [2435.9912109375]\n", + "epsilon:0.11018311023500525 step:875 episode:44 last_score -23.702634887695318 Profit 0.0 Loss [3611.1943359375]\n", + "epsilon:0.11018311023500525 step:880 episode:44 last_score -23.702634887695318 Profit 0.0 Loss [2205.237060546875]\n", + "epsilon:0.10467395472325498 step:885 episode:45 last_score -36.1008462524414 Profit 0.0 Loss [2316.9560546875]\n", + "epsilon:0.10467395472325498 step:890 episode:45 last_score -36.1008462524414 Profit 0.0 Loss [1841.0050048828125]\n", + "epsilon:0.10467395472325498 step:895 episode:45 last_score -36.1008462524414 Profit -31.45599365234375 Loss [1126.6566162109375]\n", + "epsilon:0.10467395472325498 step:900 episode:45 last_score -36.1008462524414 Profit -31.45599365234375 Loss [2535.717529296875]\n", + "epsilon:0.09944025698709223 step:905 episode:46 last_score -138.84541503906252 Profit 0.0 Loss [1664.5146484375]\n", + "epsilon:0.09944025698709223 step:910 episode:46 last_score -138.84541503906252 Profit -43.793701171875 Loss [1393.802978515625]\n", + "epsilon:0.09944025698709223 step:915 episode:46 last_score -138.84541503906252 Profit -43.793701171875 Loss [1892.80517578125]\n", + "epsilon:0.09944025698709223 step:920 episode:46 last_score -138.84541503906252 Profit -43.793701171875 Loss [2296.464599609375]\n", + "epsilon:0.09446824413773762 step:925 episode:47 last_score -372.9497229003906 Profit 0.0 Loss [2797.4091796875]\n", + "epsilon:0.09446824413773762 step:930 episode:47 last_score -372.9497229003906 Profit 0.0 Loss [1596.3612060546875]\n", + "epsilon:0.09446824413773762 step:935 episode:47 last_score -372.9497229003906 Profit 0.0 Loss [3025.2255859375]\n", + "epsilon:0.09446824413773762 step:940 episode:47 last_score -372.9497229003906 Profit 0.0 Loss [2103.651123046875]\n", + "epsilon:0.08974483193085074 step:945 episode:48 last_score -315.3049487304687 Profit 0.0 Loss [1752.3865966796875]\n", + "epsilon:0.08974483193085074 step:950 episode:48 last_score -315.3049487304687 Profit 0.0 Loss [3352.652587890625]\n", + "epsilon:0.08974483193085074 step:955 episode:48 last_score -315.3049487304687 Profit 0.0 Loss [4115.0986328125]\n", + "epsilon:0.08974483193085074 step:960 episode:48 last_score -315.3049487304687 Profit 0.0 Loss [3944.266845703125]\n", + "epsilon:0.0852575903343082 step:965 episode:49 last_score -129.73040283203127 Profit 0.0 Loss [2007.557861328125]\n", + "epsilon:0.0852575903343082 step:970 episode:49 last_score -129.73040283203127 Profit 23.2025146484375 Loss [5351.98876953125]\n", + "epsilon:0.0852575903343082 step:975 episode:49 last_score -129.73040283203127 Profit 23.2025146484375 Loss [2888.251220703125]\n", + "epsilon:0.0852575903343082 step:980 episode:49 last_score -129.73040283203127 Profit 67.87358093261719 Loss [3609.883056640625]\n", + "epsilon:0.08099471081759278 step:985 episode:50 last_score 41.64497634887695 Profit 0.0 Loss [2919.0322265625]\n", + "epsilon:0.08099471081759278 step:990 episode:50 last_score 41.64497634887695 Profit 0.0 Loss [3385.35009765625]\n", + "epsilon:0.08099471081759278 step:995 episode:50 last_score 41.64497634887695 Profit 0.0 Loss [2275.793212890625]\n", + "epsilon:0.08099471081759278 step:1000 episode:50 last_score 41.64497634887695 Profit 0.0 Loss [1812.9034423828125]\n", + "epsilon:0.07694497527671314 step:1005 episode:51 last_score -312.6370520019531 Profit 25.8341064453125 Loss [2228.8681640625]\n", + "epsilon:0.07694497527671314 step:1010 episode:51 last_score -312.6370520019531 Profit 86.1837158203125 Loss [2413.616455078125]\n", + "epsilon:0.07694497527671314 step:1015 episode:51 last_score -312.6370520019531 Profit 51.3143310546875 Loss [1864.9190673828125]\n", + "epsilon:0.07694497527671314 step:1020 episode:51 last_score -312.6370520019531 Profit 86.9190673828125 Loss [2256.05712890625]\n", + "epsilon:0.07309772651287748 step:1025 episode:52 last_score -120.16126586914064 Profit 0.0 Loss [2518.8115234375]\n", + "epsilon:0.07309772651287748 step:1030 episode:52 last_score -120.16126586914064 Profit 0.0 Loss [1895.2779541015625]\n", + "epsilon:0.07309772651287748 step:1035 episode:52 last_score -120.16126586914064 Profit 0.0 Loss [1916.77587890625]\n", + "epsilon:0.07309772651287748 step:1040 episode:52 last_score -120.16126586914064 Profit 0.0 Loss [1260.976318359375]\n", + "epsilon:0.0694428401872336 step:1045 episode:53 last_score -787.0493847656252 Profit 11.1455078125 Loss [1558.4332275390625]\n", + "epsilon:0.0694428401872336 step:1050 episode:53 last_score -787.0493847656252 Profit 192.385009765625 Loss [3267.190673828125]\n", + "epsilon:0.0694428401872336 step:1055 episode:53 last_score -787.0493847656252 Profit 192.385009765625 Loss [3873.492919921875]\n", + "epsilon:0.0694428401872336 step:1060 episode:53 last_score -787.0493847656252 Profit 255.745849609375 Loss [4078.318359375]\n", + "epsilon:0.0659706981778719 step:1065 episode:54 last_score 2.120605468749986 Profit 0.0 Loss [1493.6756591796875]\n", + "epsilon:0.0659706981778719 step:1070 episode:54 last_score 2.120605468749986 Profit 122.44998168945312 Loss [2609.72021484375]\n", + "epsilon:0.0659706981778719 step:1075 episode:54 last_score 2.120605468749986 Profit 122.44998168945312 Loss [1359.8560791015625]\n", + "epsilon:0.0659706981778719 step:1080 episode:54 last_score 2.120605468749986 Profit 122.44998168945312 Loss [2881.857421875]\n", + "epsilon:0.0626721632689783 step:1085 episode:55 last_score 17.55906311035155 Profit 0.0 Loss [2777.1181640625]\n", + "epsilon:0.0626721632689783 step:1090 episode:55 last_score 17.55906311035155 Profit 408.433837890625 Loss [709.6217041015625]\n", + "epsilon:0.0626721632689783 step:1095 episode:55 last_score 17.55906311035155 Profit 408.433837890625 Loss [1722.9761962890625]\n", + "epsilon:0.0626721632689783 step:1100 episode:55 last_score 17.55906311035155 Profit 921.958984375 Loss [1415.93701171875]\n", + "epsilon:0.059538555105529384 step:1105 episode:56 last_score 363.2361791992187 Profit 0.0 Loss [1033.850830078125]\n", + "epsilon:0.059538555105529384 step:1110 episode:56 last_score 363.2361791992187 Profit 130.072021484375 Loss [1577.04248046875]\n", + "epsilon:0.059538555105529384 step:1115 episode:56 last_score 363.2361791992187 Profit 130.072021484375 Loss [3740.52880859375]\n", + "epsilon:0.059538555105529384 step:1120 episode:56 last_score 363.2361791992187 Profit 261.81298828125 Loss [2299.3896484375]\n", + "epsilon:0.05656162735025291 step:1125 episode:57 last_score 175.4292498779297 Profit -2.0260009765625 Loss [2161.370849609375]\n", + "epsilon:0.05656162735025291 step:1130 episode:57 last_score 175.4292498779297 Profit -2.0260009765625 Loss [2135.614501953125]\n", + "epsilon:0.05656162735025291 step:1135 episode:57 last_score 175.4292498779297 Profit -2.0260009765625 Loss [1773.0596923828125]\n", + "epsilon:0.05656162735025291 step:1140 episode:57 last_score 175.4292498779297 Profit -2.0260009765625 Loss [1806.198486328125]\n", + "epsilon:0.053733545982740265 step:1145 episode:58 last_score -150.64427734375005 Profit 0.0 Loss [2040.107666015625]\n", + "epsilon:0.053733545982740265 step:1150 episode:58 last_score -150.64427734375005 Profit 513.274658203125 Loss [2773.68212890625]\n", + "epsilon:0.053733545982740265 step:1155 episode:58 last_score -150.64427734375005 Profit 917.051513671875 Loss [2700.312744140625]\n", + "epsilon:0.053733545982740265 step:1160 episode:58 last_score -150.64427734375005 Profit 1529.35302734375 Loss [1446.0665283203125]\n", + "epsilon:0.05104686868360325 step:1165 episode:59 last_score 1810.7448095703126 Profit 0.0 Loss [1545.9669189453125]\n", + "epsilon:0.05104686868360325 step:1170 episode:59 last_score 1810.7448095703126 Profit 42.574981689453125 Loss [2363.37060546875]\n", + "epsilon:0.05104686868360325 step:1175 episode:59 last_score 1810.7448095703126 Profit 72.34597778320312 Loss [2315.095458984375]\n", + "epsilon:0.05104686868360325 step:1180 episode:59 last_score 1810.7448095703126 Profit 61.913970947265625 Loss [1094.87646484375]\n", + "epsilon:0.04849452524942309 step:1185 episode:60 last_score 23.27654571533203 Profit 0.0 Loss [3523.248779296875]\n", + "epsilon:0.04849452524942309 step:1190 episode:60 last_score 23.27654571533203 Profit -9.745147705078125 Loss [847.3668823242188]\n", + "epsilon:0.04849452524942309 step:1195 episode:60 last_score 23.27654571533203 Profit -2.3974151611328125 Loss [1319.2894287109375]\n", + "epsilon:0.04849452524942309 step:1200 episode:60 last_score 23.27654571533203 Profit -2.3974151611328125 Loss [1507.8603515625]\n", + "epsilon:0.04606979898695193 step:1205 episode:61 last_score -31.92987945556641 Profit -12.291183471679688 Loss [1694.032470703125]\n", + "epsilon:0.04606979898695193 step:1210 episode:61 last_score -31.92987945556641 Profit -5.005340576171875 Loss [1477.3397216796875]\n", + "epsilon:0.04606979898695193 step:1215 episode:61 last_score -31.92987945556641 Profit -5.005340576171875 Loss [3519.620361328125]\n", + "epsilon:0.04606979898695193 step:1220 episode:61 last_score -31.92987945556641 Profit 6.1326904296875 Loss [2347.724365234375]\n", + "epsilon:0.04376630903760433 step:1225 episode:62 last_score -19.44420135498047 Profit 0.0 Loss [1061.556884765625]\n", + "epsilon:0.04376630903760433 step:1230 episode:62 last_score -19.44420135498047 Profit 0.0 Loss [2243.763671875]\n", + "epsilon:0.04376630903760433 step:1235 episode:62 last_score -19.44420135498047 Profit -11.2548828125 Loss [1870.0177001953125]\n", + "epsilon:0.04376630903760433 step:1240 episode:62 last_score -19.44420135498047 Profit -7.9685821533203125 Loss [3528.5078125]\n", + "epsilon:0.041577993585724116 step:1245 episode:63 last_score -25.887432250976566 Profit 0.0 Loss [2264.726806640625]\n", + "epsilon:0.041577993585724116 step:1250 episode:63 last_score -25.887432250976566 Profit 0.0 Loss [2107.2373046875]\n", + "epsilon:0.041577993585724116 step:1255 episode:63 last_score -25.887432250976566 Profit 31.218109130859375 Loss [2628.636962890625]\n", + "epsilon:0.041577993585724116 step:1260 episode:63 last_score -25.887432250976566 Profit 31.218109130859375 Loss [2644.69970703125]\n", + "epsilon:0.03949909390643791 step:1265 episode:64 last_score -4.656906433105471 Profit -4.251556396484375 Loss [1878.155029296875]\n", + "epsilon:0.03949909390643791 step:1270 episode:64 last_score -4.656906433105471 Profit -4.251556396484375 Loss [2906.493408203125]\n", + "epsilon:0.03949909390643791 step:1275 episode:64 last_score -4.656906433105471 Profit -4.251556396484375 Loss [2027.8084716796875]\n", + "epsilon:0.03949909390643791 step:1280 episode:64 last_score -4.656906433105471 Profit 7.4248809814453125 Loss [1851.9940185546875]\n", + "epsilon:0.03752413921111601 step:1285 episode:65 last_score -15.19986602783203 Profit 24.150894165039062 Loss [1929.6502685546875]\n", + "epsilon:0.03752413921111601 step:1290 episode:65 last_score -15.19986602783203 Profit 24.150894165039062 Loss [967.1546630859375]\n", + "epsilon:0.03752413921111601 step:1295 episode:65 last_score -15.19986602783203 Profit 26.55579376220703 Loss [1356.1324462890625]\n", + "epsilon:0.03752413921111601 step:1300 episode:65 last_score -15.19986602783203 Profit 26.55579376220703 Loss [1028.14306640625]\n", + "epsilon:0.03564793225056021 step:1305 episode:66 last_score 6.253561553955077 Profit 0.0 Loss [1019.1090698242188]\n", + "epsilon:0.03564793225056021 step:1310 episode:66 last_score 6.253561553955077 Profit 540.18896484375 Loss [1798.157470703125]\n", + "epsilon:0.03564793225056021 step:1315 episode:66 last_score 6.253561553955077 Profit 507.91943359375 Loss [1922.5277099609375]\n", + "epsilon:0.03564793225056021 step:1320 episode:66 last_score 6.253561553955077 Profit 507.91943359375 Loss [2492.54150390625]\n", + "epsilon:0.0338655356380322 step:1325 episode:67 last_score 261.19353759765636 Profit 269.91015625 Loss [2263.058837890625]\n", + "epsilon:0.0338655356380322 step:1330 episode:67 last_score 261.19353759765636 Profit 538.9921875 Loss [2172.87744140625]\n", + "epsilon:0.0338655356380322 step:1335 episode:67 last_score 261.19353759765636 Profit 538.9921875 Loss [1564.30078125]\n", + "epsilon:0.0338655356380322 step:1340 episode:67 last_score 261.19353759765636 Profit 538.9921875 Loss [2202.201171875]\n", + "epsilon:0.032172258856130585 step:1345 episode:68 last_score 278.3053540039062 Profit 0.0 Loss [2384.120361328125]\n", + "epsilon:0.032172258856130585 step:1350 episode:68 last_score 278.3053540039062 Profit 0.0 Loss [4880.10986328125]\n", + "epsilon:0.032172258856130585 step:1355 episode:68 last_score 278.3053540039062 Profit 106.51602172851562 Loss [3111.831298828125]\n", + "epsilon:0.032172258856130585 step:1360 episode:68 last_score 278.3053540039062 Profit 106.51602172851562 Loss [3146.927490234375]\n", + "epsilon:0.030563645913324056 step:1365 episode:69 last_score 48.83006713867188 Profit 7.564300537109375 Loss [2616.340576171875]\n", + "epsilon:0.030563645913324056 step:1370 episode:69 last_score 48.83006713867188 Profit 7.564300537109375 Loss [2816.947509765625]\n", + "epsilon:0.030563645913324056 step:1375 episode:69 last_score 48.83006713867188 Profit 7.564300537109375 Loss [2560.73095703125]\n", + "epsilon:0.030563645913324056 step:1380 episode:69 last_score 48.83006713867188 Profit 19.551849365234375 Loss [1343.7249755859375]\n", + "epsilon:0.029035463617657853 step:1385 episode:70 last_score -14.93466354370117 Profit 0.0 Loss [2279.232421875]\n", + "epsilon:0.029035463617657853 step:1390 episode:70 last_score -14.93466354370117 Profit 0.0 Loss [2755.838134765625]\n", + "epsilon:0.029035463617657853 step:1395 episode:70 last_score -14.93466354370117 Profit 0.0 Loss [2926.527099609375]\n", + "epsilon:0.029035463617657853 step:1400 episode:70 last_score -14.93466354370117 Profit 0.0 Loss [2701.531005859375]\n", + "epsilon:0.027583690436774957 step:1405 episode:71 last_score -43.62907745361328 Profit 0.0 Loss [1888.9512939453125]\n", + "epsilon:0.027583690436774957 step:1410 episode:71 last_score -43.62907745361328 Profit 0.0 Loss [1140.7774658203125]\n", + "epsilon:0.027583690436774957 step:1415 episode:71 last_score -43.62907745361328 Profit 0.0 Loss [1410.911376953125]\n", + "epsilon:0.027583690436774957 step:1420 episode:71 last_score -43.62907745361328 Profit 0.0 Loss [2821.482421875]\n", + "epsilon:0.02620450591493621 step:1425 episode:72 last_score -342.7034106445313 Profit 0.0 Loss [2573.23291015625]\n", + "epsilon:0.02620450591493621 step:1430 episode:72 last_score -342.7034106445313 Profit 0.0 Loss [1958.0379638671875]\n", + "epsilon:0.02620450591493621 step:1435 episode:72 last_score -342.7034106445313 Profit 452.537109375 Loss [3386.053466796875]\n", + "epsilon:0.02620450591493621 step:1440 episode:72 last_score -342.7034106445313 Profit 629.17041015625 Loss [1810.0228271484375]\n", + "epsilon:0.0248942806191894 step:1445 episode:73 last_score 36.665373535156284 Profit 56.928009033203125 Loss [1677.8790283203125]\n", + "epsilon:0.0248942806191894 step:1450 episode:73 last_score 36.665373535156284 Profit 56.928009033203125 Loss [2088.1015625]\n", + "epsilon:0.0248942806191894 step:1455 episode:73 last_score 36.665373535156284 Profit 49.787017822265625 Loss [2066.905029296875]\n", + "epsilon:0.0248942806191894 step:1460 episode:73 last_score 36.665373535156284 Profit 45.78501892089844 Loss [1904.9697265625]\n", + "epsilon:0.023649566588229927 step:1465 episode:74 last_score 37.68025497436524 Profit 11.36669921875 Loss [2129.84814453125]\n", + "epsilon:0.023649566588229927 step:1470 episode:74 last_score 37.68025497436524 Profit 17.185638427734375 Loss [1553.2041015625]\n", + "epsilon:0.023649566588229927 step:1475 episode:74 last_score 37.68025497436524 Profit 17.185638427734375 Loss [2797.148193359375]\n", + "epsilon:0.023649566588229927 step:1480 episode:74 last_score 37.68025497436524 Profit 17.185638427734375 Loss [2764.87939453125]\n", + "epsilon:0.022467088258818428 step:1485 episode:75 last_score 3.697814025878908 Profit 0.0 Loss [3239.05029296875]\n", + "epsilon:0.022467088258818428 step:1490 episode:75 last_score 3.697814025878908 Profit 0.0 Loss [1833.561279296875]\n", + "epsilon:0.022467088258818428 step:1495 episode:75 last_score 3.697814025878908 Profit 0.0 Loss [3836.063720703125]\n", + "epsilon:0.022467088258818428 step:1500 episode:75 last_score 3.697814025878908 Profit 792.9501953125 Loss [1410.4462890625]\n", + "epsilon:0.021343733845877507 step:1505 episode:76 last_score -417.4258374023436 Profit 0.0 Loss [2823.661865234375]\n", + "epsilon:0.021343733845877507 step:1510 episode:76 last_score -417.4258374023436 Profit 10.613296508789062 Loss [2733.33349609375]\n", + "epsilon:0.021343733845877507 step:1515 episode:76 last_score -417.4258374023436 Profit 19.099884033203125 Loss [1295.875732421875]\n", + "epsilon:0.021343733845877507 step:1520 episode:76 last_score -417.4258374023436 Profit 25.432235717773438 Loss [2059.1318359375]\n", + "epsilon:0.02027654715358363 step:1525 episode:77 last_score 16.35025894165039 Profit -6.46197509765625 Loss [1049.21826171875]\n", + "epsilon:0.02027654715358363 step:1530 episode:77 last_score 16.35025894165039 Profit -6.46197509765625 Loss [1950.97119140625]\n", + "epsilon:0.02027654715358363 step:1535 episode:77 last_score 16.35025894165039 Profit 125.27899169921875 Loss [1857.91064453125]\n", + "epsilon:0.02027654715358363 step:1540 episode:77 last_score 16.35025894165039 Profit 125.27899169921875 Loss [749.6634521484375]\n", + "epsilon:0.019262719795904448 step:1545 episode:78 last_score 25.740966186523448 Profit 0.0 Loss [2982.456298828125]\n", + "epsilon:0.019262719795904448 step:1550 episode:78 last_score 25.740966186523448 Profit 0.0 Loss [2980.451904296875]\n", + "epsilon:0.019262719795904448 step:1555 episode:78 last_score 25.740966186523448 Profit 0.0 Loss [1670.703125]\n", + "epsilon:0.019262719795904448 step:1560 episode:78 last_score 25.740966186523448 Profit 0.0 Loss [1702.888427734375]\n", + "epsilon:0.018299583806109226 step:1565 episode:79 last_score -56.323187561035155 Profit 0.0 Loss [3174.088134765625]\n", + "epsilon:0.018299583806109226 step:1570 episode:79 last_score -56.323187561035155 Profit 0.0 Loss [1582.7633056640625]\n", + "epsilon:0.018299583806109226 step:1575 episode:79 last_score -56.323187561035155 Profit 0.0 Loss [2768.8623046875]\n", + "epsilon:0.018299583806109226 step:1580 episode:79 last_score -56.323187561035155 Profit 0.0 Loss [2915.33056640625]\n", + "epsilon:0.017384604615803764 step:1585 episode:80 last_score -65.55392578124997 Profit 177.8310546875 Loss [1457.9981689453125]\n", + "epsilon:0.017384604615803764 step:1590 episode:80 last_score -65.55392578124997 Profit 514.8564453125 Loss [3702.977294921875]\n", + "epsilon:0.017384604615803764 step:1595 episode:80 last_score -65.55392578124997 Profit 859.84814453125 Loss [3894.68408203125]\n", + "epsilon:0.017384604615803764 step:1600 episode:80 last_score -65.55392578124997 Profit 1214.753662109375 Loss [3094.5625]\n", + "epsilon:0.016515374385013576 step:1605 episode:81 last_score 1241.7112499999998 Profit 0.0 Loss [2078.083251953125]\n", + "epsilon:0.016515374385013576 step:1610 episode:81 last_score 1241.7112499999998 Profit 466.128662109375 Loss [2256.103515625]\n", + "epsilon:0.016515374385013576 step:1615 episode:81 last_score 1241.7112499999998 Profit 466.128662109375 Loss [1616.602783203125]\n", + "epsilon:0.016515374385013576 step:1620 episode:81 last_score 1241.7112499999998 Profit 391.9140625 Loss [3349.1435546875]\n", + "epsilon:0.015689605665762895 step:1625 episode:82 last_score -112.22800781250001 Profit 246.398193359375 Loss [1315.56396484375]\n", + "epsilon:0.015689605665762895 step:1630 episode:82 last_score -112.22800781250001 Profit 665.359375 Loss [2865.593505859375]\n", + "epsilon:0.015689605665762895 step:1635 episode:82 last_score -112.22800781250001 Profit 807.171875 Loss [2442.416259765625]\n", + "epsilon:0.015689605665762895 step:1640 episode:82 last_score -112.22800781250001 Profit 764.142578125 Loss [1871.4769287109375]\n", + "epsilon:0.01490512538247475 step:1645 episode:83 last_score 686.2460644531249 Profit 40.90679931640625 Loss [2723.986572265625]\n", + "epsilon:0.01490512538247475 step:1650 episode:83 last_score 686.2460644531249 Profit 40.90679931640625 Loss [1684.6021728515625]\n", + "epsilon:0.01490512538247475 step:1655 episode:83 last_score 686.2460644531249 Profit 40.90679931640625 Loss [1698.809814453125]\n", + "epsilon:0.01490512538247475 step:1660 episode:83 last_score 686.2460644531249 Profit 40.90679931640625 Loss [2946.00634765625]\n", + "epsilon:0.014159869113351011 step:1665 episode:84 last_score -160.9028076171875 Profit 0.0 Loss [724.5333862304688]\n", + "epsilon:0.014159869113351011 step:1670 episode:84 last_score -160.9028076171875 Profit 0.0 Loss [2610.375]\n", + "epsilon:0.014159869113351011 step:1675 episode:84 last_score -160.9028076171875 Profit -12.049270629882812 Loss [1474.3699951171875]\n", + "epsilon:0.014159869113351011 step:1680 episode:84 last_score -160.9028076171875 Profit -12.049270629882812 Loss [2436.5380859375]\n", + "epsilon:0.01345187565768346 step:1685 episode:85 last_score -58.789067840576166 Profit 0.0 Loss [3064.419921875]\n", + "epsilon:0.01345187565768346 step:1690 episode:85 last_score -58.789067840576166 Profit 0.0 Loss [1325.5362548828125]\n", + "epsilon:0.01345187565768346 step:1695 episode:85 last_score -58.789067840576166 Profit 0.0 Loss [1942.7281494140625]\n", + "epsilon:0.01345187565768346 step:1700 episode:85 last_score -58.789067840576166 Profit 0.0 Loss [1762.068115234375]\n", + "epsilon:0.012779281874799287 step:1705 episode:86 last_score -485.0546545410156 Profit 7.28558349609375 Loss [3328.831298828125]\n", + "epsilon:0.012779281874799287 step:1710 episode:86 last_score -485.0546545410156 Profit 18.431610107421875 Loss [2821.4404296875]\n", + "epsilon:0.012779281874799287 step:1715 episode:86 last_score -485.0546545410156 Profit 18.431610107421875 Loss [1921.7515869140625]\n", + "epsilon:0.012779281874799287 step:1720 episode:86 last_score -485.0546545410156 Profit 18.431610107421875 Loss [1568.70703125]\n", + "epsilon:0.012140317781059323 step:1725 episode:87 last_score -37.11868438720703 Profit 0.0 Loss [1652.895263671875]\n", + "epsilon:0.012140317781059323 step:1730 episode:87 last_score -37.11868438720703 Profit 0.0 Loss [2760.88134765625]\n", + "epsilon:0.012140317781059323 step:1735 episode:87 last_score -37.11868438720703 Profit 0.0 Loss [1581.9879150390625]\n", + "epsilon:0.012140317781059323 step:1740 episode:87 last_score -37.11868438720703 Profit 0.0 Loss [1489.110595703125]\n", + "epsilon:0.011533301892006355 step:1745 episode:88 last_score -149.51944641113278 Profit 0.0 Loss [3696.22900390625]\n", + "epsilon:0.011533301892006355 step:1750 episode:88 last_score -149.51944641113278 Profit 0.0 Loss [1833.7159423828125]\n", + "epsilon:0.011533301892006355 step:1755 episode:88 last_score -149.51944641113278 Profit -169.2459716796875 Loss [3102.938720703125]\n", + "epsilon:0.011533301892006355 step:1760 episode:88 last_score -149.51944641113278 Profit -169.2459716796875 Loss [1582.1875]\n", + "epsilon:0.010956636797406038 step:1765 episode:89 last_score -421.52846435546877 Profit 0.0 Loss [4710.806640625]\n", + "epsilon:0.010956636797406038 step:1770 episode:89 last_score -421.52846435546877 Profit 0.0 Loss [1844.6697998046875]\n", + "epsilon:0.010956636797406038 step:1775 episode:89 last_score -421.52846435546877 Profit 0.0 Loss [3758.773193359375]\n", + "epsilon:0.010956636797406038 step:1780 episode:89 last_score -421.52846435546877 Profit 0.0 Loss [1434.2783203125]\n", + "epsilon:0.010408804957535735 step:1785 episode:90 last_score -72.12004760742188 Profit 0.0 Loss [4196.41162109375]\n", + "epsilon:0.010408804957535735 step:1790 episode:90 last_score -72.12004760742188 Profit 0.0 Loss [3106.764404296875]\n", + "epsilon:0.010408804957535735 step:1795 episode:90 last_score -72.12004760742188 Profit 0.0 Loss [1723.489013671875]\n", + "epsilon:0.010408804957535735 step:1800 episode:90 last_score -72.12004760742188 Profit 0.0 Loss [2233.632568359375]\n", + "epsilon:0.009888364709658948 step:1805 episode:91 last_score -35.14291381835937 Profit 0.0 Loss [1831.6412353515625]\n", + "epsilon:0.009888364709658948 step:1810 episode:91 last_score -35.14291381835937 Profit 27.013412475585938 Loss [2725.4482421875]\n", + "epsilon:0.009888364709658948 step:1815 episode:91 last_score -35.14291381835937 Profit 27.013412475585938 Loss [3206.85595703125]\n", + "epsilon:0.009888364709658948 step:1820 episode:91 last_score -35.14291381835937 Profit 27.013412475585938 Loss [1812.4464111328125]\n", + "epsilon:0.009393946474176 step:1825 episode:92 last_score 1.4481333923339825 Profit 0.0 Loss [3863.814453125]\n", + "epsilon:0.009393946474176 step:1830 episode:92 last_score 1.4481333923339825 Profit 0.0 Loss [2657.74755859375]\n", + "epsilon:0.009393946474176 step:1835 episode:92 last_score 1.4481333923339825 Profit 7.662689208984375 Loss [1523.4473876953125]\n", + "epsilon:0.009393946474176 step:1840 episode:92 last_score 1.4481333923339825 Profit 5.7172088623046875 Loss [1583.1209716796875]\n", + "epsilon:0.0089242491504672 step:1845 episode:93 last_score -4.855594787597658 Profit 0.0 Loss [2209.89208984375]\n", + "epsilon:0.0089242491504672 step:1850 episode:93 last_score -4.855594787597658 Profit 0.0 Loss [1936.345458984375]\n", + "epsilon:0.0089242491504672 step:1855 episode:93 last_score -4.855594787597658 Profit 0.0 Loss [2572.5087890625]\n", + "epsilon:0.0089242491504672 step:1860 episode:93 last_score -4.855594787597658 Profit 0.0 Loss [925.7698364257812]\n", + "epsilon:0.008478036692943839 step:1865 episode:94 last_score -80.26002716064451 Profit 0.0 Loss [1778.219970703125]\n", + "epsilon:0.008478036692943839 step:1870 episode:94 last_score -80.26002716064451 Profit 0.0 Loss [2342.25537109375]\n", + "epsilon:0.008478036692943839 step:1875 episode:94 last_score -80.26002716064451 Profit 0.0 Loss [3987.734130859375]\n", + "epsilon:0.008478036692943839 step:1880 episode:94 last_score -80.26002716064451 Profit 0.0 Loss [2281.66650390625]\n", + "epsilon:0.008054134858296647 step:1885 episode:95 last_score -84.1945690917969 Profit 0.0 Loss [2494.296142578125]\n", + "epsilon:0.008054134858296647 step:1890 episode:95 last_score -84.1945690917969 Profit 0.0 Loss [691.982666015625]\n", + "epsilon:0.008054134858296647 step:1895 episode:95 last_score -84.1945690917969 Profit 0.0 Loss [2512.132080078125]\n", + "epsilon:0.008054134858296647 step:1900 episode:95 last_score -84.1945690917969 Profit 0.0 Loss [1541.190185546875]\n", + "epsilon:0.0076514281153818135 step:1905 episode:96 last_score -900.6443969726563 Profit 272.029541015625 Loss [1366.616455078125]\n", + "epsilon:0.0076514281153818135 step:1910 episode:96 last_score -900.6443969726563 Profit 272.029541015625 Loss [1639.6121826171875]\n", + "epsilon:0.0076514281153818135 step:1915 episode:96 last_score -900.6443969726563 Profit 272.029541015625 Loss [3593.957763671875]\n", + "epsilon:0.0076514281153818135 step:1920 episode:96 last_score -900.6443969726563 Profit 272.029541015625 Loss [3383.4306640625]\n", + "epsilon:0.0072688567096127225 step:1925 episode:97 last_score -64.36495605468753 Profit 0.0 Loss [1309.880615234375]\n", + "epsilon:0.0072688567096127225 step:1930 episode:97 last_score -64.36495605468753 Profit 0.0 Loss [2274.544677734375]\n", + "epsilon:0.0072688567096127225 step:1935 episode:97 last_score -64.36495605468753 Profit 0.0 Loss [1738.5640869140625]\n", + "epsilon:0.0072688567096127225 step:1940 episode:97 last_score -64.36495605468753 Profit 0.0 Loss [1708.520263671875]\n", + "epsilon:0.006905413874132086 step:1945 episode:98 last_score -43.76183410644532 Profit 0.0 Loss [1243.618896484375]\n", + "epsilon:0.006905413874132086 step:1950 episode:98 last_score -43.76183410644532 Profit 0.0 Loss [1445.91015625]\n", + "epsilon:0.006905413874132086 step:1955 episode:98 last_score -43.76183410644532 Profit 0.0 Loss [1964.3477783203125]\n", + "epsilon:0.006905413874132086 step:1960 episode:98 last_score -43.76183410644532 Profit 0.0 Loss [4264.35986328125]\n", + "epsilon:0.006560143180425482 step:1965 episode:99 last_score -85.18000213623047 Profit 0.0 Loss [1863.7872314453125]\n", + "epsilon:0.006560143180425482 step:1970 episode:99 last_score -85.18000213623047 Profit 0.0 Loss [1739.552001953125]\n", + "epsilon:0.006560143180425482 step:1975 episode:99 last_score -85.18000213623047 Profit 0.0 Loss [1861.4112548828125]\n", + "epsilon:0.006560143180425482 step:1980 episode:99 last_score -85.18000213623047 Profit 0.0 Loss [2906.19873046875]\n", + "epsilon:0.0062321360214042075 step:1985 episode:100 last_score -44.56894165039062 Profit 0.0 Loss [2862.763671875]\n", + "epsilon:0.0062321360214042075 step:1990 episode:100 last_score -44.56894165039062 Profit 0.0 Loss [1943.927490234375]\n", + "epsilon:0.0062321360214042075 step:1995 episode:100 last_score -44.56894165039062 Profit 0.0 Loss [1851.90576171875]\n", + "epsilon:0.0062321360214042075 step:2000 episode:100 last_score -44.56894165039062 Profit 0.0 Loss [2406.13720703125]\n", + "epsilon:0.005920529220333997 step:2005 episode:101 last_score -25.657330169677735 Profit 0.0 Loss [3531.843994140625]\n", + "epsilon:0.005920529220333997 step:2010 episode:101 last_score -25.657330169677735 Profit 0.0 Loss [2198.40380859375]\n", + "epsilon:0.005920529220333997 step:2015 episode:101 last_score -25.657330169677735 Profit 0.0 Loss [1213.93212890625]\n", + "epsilon:0.005920529220333997 step:2020 episode:101 last_score -25.657330169677735 Profit 0.0 Loss [1279.8421630859375]\n", + "epsilon:0.0056245027593172965 step:2025 episode:102 last_score -284.74399719238284 Profit 0.0 Loss [2842.04052734375]\n", + "epsilon:0.0056245027593172965 step:2030 episode:102 last_score -284.74399719238284 Profit 0.0 Loss [3342.888671875]\n", + "epsilon:0.0056245027593172965 step:2035 episode:102 last_score -284.74399719238284 Profit 0.0 Loss [2845.420654296875]\n", + "epsilon:0.0056245027593172965 step:2040 episode:102 last_score -284.74399719238284 Profit 0.0 Loss [732.1626586914062]\n", + "epsilon:0.005343277621351432 step:2045 episode:103 last_score -43.75862060546875 Profit 0.0 Loss [2870.701904296875]\n", + "epsilon:0.005343277621351432 step:2050 episode:103 last_score -43.75862060546875 Profit 0.0 Loss [3466.960205078125]\n", + "epsilon:0.005343277621351432 step:2055 episode:103 last_score -43.75862060546875 Profit 0.0 Loss [1397.685302734375]\n", + "epsilon:0.005343277621351432 step:2060 episode:103 last_score -43.75862060546875 Profit 0.0 Loss [1687.9749755859375]\n", + "epsilon:0.0050761137402838595 step:2065 episode:104 last_score -627.4983911132812 Profit 0.0 Loss [1315.11181640625]\n", + "epsilon:0.0050761137402838595 step:2070 episode:104 last_score -627.4983911132812 Profit 0.0 Loss [2851.050537109375]\n", + "epsilon:0.0050761137402838595 step:2075 episode:104 last_score -627.4983911132812 Profit 0.0 Loss [3067.4453125]\n", + "epsilon:0.0050761137402838595 step:2080 episode:104 last_score -627.4983911132812 Profit 0.0 Loss [1556.6949462890625]\n", + "epsilon:0.004822308053269666 step:2085 episode:105 last_score -36.1008462524414 Profit 0.0 Loss [1399.4876708984375]\n", + "epsilon:0.004822308053269666 step:2090 episode:105 last_score -36.1008462524414 Profit 0.0 Loss [1621.2236328125]\n", + "epsilon:0.004822308053269666 step:2095 episode:105 last_score -36.1008462524414 Profit 0.0 Loss [1626.5322265625]\n", + "epsilon:0.004822308053269666 step:2100 episode:105 last_score -36.1008462524414 Profit 0.0 Loss [2808.28759765625]\n", + "epsilon:0.004581192650606183 step:2105 episode:106 last_score -186.05002014160158 Profit 0.0 Loss [2878.598388671875]\n", + "epsilon:0.004581192650606183 step:2110 episode:106 last_score -186.05002014160158 Profit 0.0 Loss [2950.57568359375]\n", + "epsilon:0.004581192650606183 step:2115 episode:106 last_score -186.05002014160158 Profit 0.0 Loss [790.8329467773438]\n", + "epsilon:0.004581192650606183 step:2120 episode:106 last_score -186.05002014160158 Profit 0.0 Loss [1732.6181640625]\n", + "epsilon:0.0043521330180758735 step:2125 episode:107 last_score -49.15030151367186 Profit 0.0 Loss [1381.2462158203125]\n", + "epsilon:0.0043521330180758735 step:2130 episode:107 last_score -49.15030151367186 Profit 0.0 Loss [1467.47314453125]\n", + "epsilon:0.0043521330180758735 step:2135 episode:107 last_score -49.15030151367186 Profit 0.0 Loss [4403.11767578125]\n", + "epsilon:0.0043521330180758735 step:2140 episode:107 last_score -49.15030151367186 Profit 0.0 Loss [1712.639404296875]\n", + "epsilon:0.0041345263671720795 step:2145 episode:108 last_score -574.74390625 Profit 0.0 Loss [1807.35986328125]\n", + "epsilon:0.0041345263671720795 step:2150 episode:108 last_score -574.74390625 Profit 0.0 Loss [1016.5777587890625]\n", + "epsilon:0.0041345263671720795 step:2155 episode:108 last_score -574.74390625 Profit 0.0 Loss [1839.359375]\n", + "epsilon:0.0041345263671720795 step:2160 episode:108 last_score -574.74390625 Profit 0.0 Loss [1479.513427734375]\n", + "epsilon:0.003927800048813475 step:2165 episode:109 last_score -257.529091796875 Profit 0.0 Loss [947.7860717773438]\n", + "epsilon:0.003927800048813475 step:2170 episode:109 last_score -257.529091796875 Profit 0.0 Loss [3227.505859375]\n", + "epsilon:0.003927800048813475 step:2175 episode:109 last_score -257.529091796875 Profit 0.0 Loss [2105.491455078125]\n", + "epsilon:0.003927800048813475 step:2180 episode:109 last_score -257.529091796875 Profit 0.0 Loss [1004.7042236328125]\n", + "epsilon:0.0037314100463728015 step:2185 episode:110 last_score -80.26002716064451 Profit 0.0 Loss [1416.1456298828125]\n", + "epsilon:0.0037314100463728015 step:2190 episode:110 last_score -80.26002716064451 Profit 0.0 Loss [1962.188232421875]\n", + "epsilon:0.0037314100463728015 step:2195 episode:110 last_score -80.26002716064451 Profit 0.0 Loss [2216.0634765625]\n", + "epsilon:0.0037314100463728015 step:2200 episode:110 last_score -80.26002716064451 Profit 0.0 Loss [1584.8427734375]\n", + "epsilon:0.0035448395440541612 step:2205 episode:111 last_score -36.88951568603516 Profit 0.0 Loss [2434.82177734375]\n", + "epsilon:0.0035448395440541612 step:2210 episode:111 last_score -36.88951568603516 Profit 0.0 Loss [819.3399047851562]\n", + "epsilon:0.0035448395440541612 step:2215 episode:111 last_score -36.88951568603516 Profit 0.0 Loss [2064.2978515625]\n", + "epsilon:0.0035448395440541612 step:2220 episode:111 last_score -36.88951568603516 Profit 0.0 Loss [1492.649658203125]\n", + "epsilon:0.003367597566851453 step:2225 episode:112 last_score -33.115298538208016 Profit 0.0 Loss [2199.51318359375]\n", + "epsilon:0.003367597566851453 step:2230 episode:112 last_score -33.115298538208016 Profit 0.0 Loss [1928.75244140625]\n", + "epsilon:0.003367597566851453 step:2235 episode:112 last_score -33.115298538208016 Profit 0.0 Loss [2004.0389404296875]\n", + "epsilon:0.003367597566851453 step:2240 episode:112 last_score -33.115298538208016 Profit 0.0 Loss [3811.580078125]\n", + "epsilon:0.00319921768850888 step:2245 episode:113 last_score -92.78257232666016 Profit 0.0 Loss [1326.260498046875]\n", + "epsilon:0.00319921768850888 step:2250 episode:113 last_score -92.78257232666016 Profit 0.0 Loss [1200.1500244140625]\n", + "epsilon:0.00319921768850888 step:2255 episode:113 last_score -92.78257232666016 Profit 0.0 Loss [3197.74072265625]\n", + "epsilon:0.00319921768850888 step:2260 episode:113 last_score -92.78257232666016 Profit 0.0 Loss [1760.3837890625]\n", + "epsilon:0.003039256804083436 step:2265 episode:114 last_score -19.579733276367193 Profit 0.0 Loss [1244.9833984375]\n", + "epsilon:0.003039256804083436 step:2270 episode:114 last_score -19.579733276367193 Profit 0.0 Loss [1939.83251953125]\n", + "epsilon:0.003039256804083436 step:2275 episode:114 last_score -19.579733276367193 Profit 0.0 Loss [1545.5467529296875]\n", + "epsilon:0.003039256804083436 step:2280 episode:114 last_score -19.579733276367193 Profit 0.0 Loss [1516.47705078125]\n", + "epsilon:0.0028872939638792637 step:2285 episode:115 last_score -85.2329556274414 Profit 0.0 Loss [997.9474487304688]\n", + "epsilon:0.0028872939638792637 step:2290 episode:115 last_score -85.2329556274414 Profit 0.0 Loss [1903.555419921875]\n", + "epsilon:0.0028872939638792637 step:2295 episode:115 last_score -85.2329556274414 Profit 0.0 Loss [2298.3603515625]\n", + "epsilon:0.0028872939638792637 step:2300 episode:115 last_score -85.2329556274414 Profit 0.0 Loss [1131.134521484375]\n", + "epsilon:0.0027429292656853004 step:2305 episode:116 last_score -85.2785272216797 Profit 0.0 Loss [1745.877197265625]\n", + "epsilon:0.0027429292656853004 step:2310 episode:116 last_score -85.2785272216797 Profit 0.0 Loss [1426.52734375]\n", + "epsilon:0.0027429292656853004 step:2315 episode:116 last_score -85.2785272216797 Profit 0.0 Loss [1298.59423828125]\n", + "epsilon:0.0027429292656853004 step:2320 episode:116 last_score -85.2785272216797 Profit 0.0 Loss [2719.054443359375]\n", + "epsilon:0.0026057828024010354 step:2325 episode:117 last_score -39.5069645690918 Profit 0.0 Loss [1988.7186279296875]\n", + "epsilon:0.0026057828024010354 step:2330 episode:117 last_score -39.5069645690918 Profit 0.0 Loss [607.4852294921875]\n", + "epsilon:0.0026057828024010354 step:2335 episode:117 last_score -39.5069645690918 Profit 0.0 Loss [1505.072021484375]\n", + "epsilon:0.0026057828024010354 step:2340 episode:117 last_score -39.5069645690918 Profit 0.0 Loss [2310.734619140625]\n", + "epsilon:0.0024754936622809836 step:2345 episode:118 last_score -65.51922454833984 Profit 0.0 Loss [2796.7626953125]\n", + "epsilon:0.0024754936622809836 step:2350 episode:118 last_score -65.51922454833984 Profit 0.0 Loss [1235.75]\n", + "epsilon:0.0024754936622809836 step:2355 episode:118 last_score -65.51922454833984 Profit 0.0 Loss [1021.7822875976562]\n", + "epsilon:0.0024754936622809836 step:2360 episode:118 last_score -65.51922454833984 Profit 0.0 Loss [3868.760009765625]\n", + "epsilon:0.002351718979166934 step:2365 episode:119 last_score -52.00002380371093 Profit 0.0 Loss [1313.2918701171875]\n", + "epsilon:0.002351718979166934 step:2370 episode:119 last_score -52.00002380371093 Profit 0.0 Loss [4314.07177734375]\n", + "epsilon:0.002351718979166934 step:2375 episode:119 last_score -52.00002380371093 Profit 0.0 Loss [811.4025268554688]\n", + "epsilon:0.002351718979166934 step:2380 episode:119 last_score -52.00002380371093 Profit 0.0 Loss [2254.598388671875]\n", + "epsilon:0.0022341330302085875 step:2385 episode:120 last_score -198.17767517089837 Profit 0.0 Loss [2198.77294921875]\n", + "epsilon:0.0022341330302085875 step:2390 episode:120 last_score -198.17767517089837 Profit 0.0 Loss [1967.516845703125]\n", + "epsilon:0.0022341330302085875 step:2395 episode:120 last_score -198.17767517089837 Profit 0.0 Loss [2135.98681640625]\n", + "epsilon:0.0022341330302085875 step:2400 episode:120 last_score -198.17767517089837 Profit 0.0 Loss [705.0792236328125]\n", + "epsilon:0.002122426378698158 step:2405 episode:121 last_score -31.901563568115236 Profit 0.0 Loss [1172.4261474609375]\n", + "epsilon:0.002122426378698158 step:2410 episode:121 last_score -31.901563568115236 Profit 0.0 Loss [2550.435546875]\n", + "epsilon:0.002122426378698158 step:2415 episode:121 last_score -31.901563568115236 Profit 0.0 Loss [827.374267578125]\n", + "epsilon:0.002122426378698158 step:2420 episode:121 last_score -31.901563568115236 Profit 0.0 Loss [2181.272216796875]\n", + "epsilon:0.0020163050597632503 step:2425 episode:122 last_score -45.03808891296388 Profit 0.0 Loss [755.9483032226562]\n", + "epsilon:0.0020163050597632503 step:2430 episode:122 last_score -45.03808891296388 Profit 0.0 Loss [1120.2562255859375]\n", + "epsilon:0.0020163050597632503 step:2435 episode:122 last_score -45.03808891296388 Profit 0.0 Loss [1223.11572265625]\n", + "epsilon:0.0020163050597632503 step:2440 episode:122 last_score -45.03808891296388 Profit 0.0 Loss [2202.38525390625]\n", + "epsilon:0.0019154898067750877 step:2445 episode:123 last_score -59.937402343749994 Profit 0.0 Loss [812.7037353515625]\n", + "epsilon:0.0019154898067750877 step:2450 episode:123 last_score -59.937402343749994 Profit 0.0 Loss [1584.47998046875]\n", + "epsilon:0.0019154898067750877 step:2455 episode:123 last_score -59.937402343749994 Profit 0.0 Loss [3314.883056640625]\n", + "epsilon:0.0019154898067750877 step:2460 episode:123 last_score -59.937402343749994 Profit 0.0 Loss [971.17919921875]\n", + "epsilon:0.0018197153164363333 step:2465 episode:124 last_score -31.99895431518555 Profit 0.0 Loss [2370.20849609375]\n", + "epsilon:0.0018197153164363333 step:2470 episode:124 last_score -31.99895431518555 Profit 0.0 Loss [1194.43896484375]\n", + "epsilon:0.0018197153164363333 step:2475 episode:124 last_score -31.99895431518555 Profit 0.0 Loss [2093.874267578125]\n", + "epsilon:0.0018197153164363333 step:2480 episode:124 last_score -31.99895431518555 Profit 0.0 Loss [803.3058471679688]\n", + "epsilon:0.0017287295506145165 step:2485 episode:125 last_score -29.011169357299803 Profit 0.0 Loss [2283.879150390625]\n", + "epsilon:0.0017287295506145165 step:2490 episode:125 last_score -29.011169357299803 Profit 0.0 Loss [611.128173828125]\n", + "epsilon:0.0017287295506145165 step:2495 episode:125 last_score -29.011169357299803 Profit 0.0 Loss [1185.04931640625]\n", + "epsilon:0.0017287295506145165 step:2500 episode:125 last_score -29.011169357299803 Profit 0.0 Loss [3195.014404296875]\n", + "epsilon:0.0016422930730837905 step:2505 episode:126 last_score -53.558800354003914 Profit 0.0 Loss [1897.087646484375]\n", + "epsilon:0.0016422930730837905 step:2510 episode:126 last_score -53.558800354003914 Profit 0.0 Loss [1336.688232421875]\n", + "epsilon:0.0016422930730837905 step:2515 episode:126 last_score -53.558800354003914 Profit 0.0 Loss [2087.9833984375]\n", + "epsilon:0.0016422930730837905 step:2520 episode:126 last_score -53.558800354003914 Profit 0.0 Loss [1452.68310546875]\n", + "epsilon:0.0015601784194296008 step:2525 episode:127 last_score -93.19946563720706 Profit 0.0 Loss [1368.1865234375]\n", + "epsilon:0.0015601784194296008 step:2530 episode:127 last_score -93.19946563720706 Profit 0.0 Loss [1311.3829345703125]\n", + "epsilon:0.0015601784194296008 step:2535 episode:127 last_score -93.19946563720706 Profit 0.0 Loss [1794.575439453125]\n", + "epsilon:0.0015601784194296008 step:2540 episode:127 last_score -93.19946563720706 Profit 0.0 Loss [671.2154541015625]\n", + "epsilon:0.0014821694984581207 step:2545 episode:128 last_score -131.43575561523437 Profit 0.0 Loss [2472.50830078125]\n", + "epsilon:0.0014821694984581207 step:2550 episode:128 last_score -131.43575561523437 Profit 0.0 Loss [1210.5584716796875]\n", + "epsilon:0.0014821694984581207 step:2555 episode:128 last_score -131.43575561523437 Profit 0.0 Loss [986.888671875]\n", + "epsilon:0.0014821694984581207 step:2560 episode:128 last_score -131.43575561523437 Profit 0.0 Loss [2299.206787109375]\n", + "epsilon:0.0014080610235352145 step:2565 episode:129 last_score -29.587902221679688 Profit 0.0 Loss [962.7483520507812]\n", + "epsilon:0.0014080610235352145 step:2570 episode:129 last_score -29.587902221679688 Profit 0.0 Loss [1644.27294921875]\n", + "epsilon:0.0014080610235352145 step:2575 episode:129 last_score -29.587902221679688 Profit 0.0 Loss [1549.9246826171875]\n", + "epsilon:0.0014080610235352145 step:2580 episode:129 last_score -29.587902221679688 Profit 0.0 Loss [1147.40673828125]\n", + "epsilon:0.0013376579723584536 step:2585 episode:130 last_score -64.76714721679687 Profit 0.0 Loss [1910.7127685546875]\n", + "epsilon:0.0013376579723584536 step:2590 episode:130 last_score -64.76714721679687 Profit 0.0 Loss [1714.9725341796875]\n", + "epsilon:0.0013376579723584536 step:2595 episode:130 last_score -64.76714721679687 Profit 0.0 Loss [1612.5206298828125]\n", + "epsilon:0.0013376579723584536 step:2600 episode:130 last_score -64.76714721679687 Profit 0.0 Loss [2077.35009765625]\n", + "epsilon:0.0012707750737405309 step:2605 episode:131 last_score -40.224028778076175 Profit 0.0 Loss [1826.5384521484375]\n", + "epsilon:0.0012707750737405309 step:2610 episode:131 last_score -40.224028778076175 Profit 0.0 Loss [1547.60546875]\n", + "epsilon:0.0012707750737405309 step:2615 episode:131 last_score -40.224028778076175 Profit 0.0 Loss [2990.840087890625]\n", + "epsilon:0.0012707750737405309 step:2620 episode:131 last_score -40.224028778076175 Profit 0.0 Loss [1730.911865234375]\n", + "epsilon:0.0012072363200535043 step:2625 episode:132 last_score -407.0245275878906 Profit 0.0 Loss [944.1072387695312]\n", + "epsilon:0.0012072363200535043 step:2630 episode:132 last_score -407.0245275878906 Profit 0.0 Loss [3333.525634765625]\n", + "epsilon:0.0012072363200535043 step:2635 episode:132 last_score -407.0245275878906 Profit 0.0 Loss [1184.779541015625]\n", + "epsilon:0.0012072363200535043 step:2640 episode:132 last_score -407.0245275878906 Profit 6.83514404296875 Loss [2650.620361328125]\n", + "epsilon:0.001146874504050829 step:2645 episode:133 last_score -8.717143707275394 Profit 0.0 Loss [1796.420166015625]\n", + "epsilon:0.001146874504050829 step:2650 episode:133 last_score -8.717143707275394 Profit 277.1201171875 Loss [1469.59521484375]\n", + "epsilon:0.001146874504050829 step:2655 episode:133 last_score -8.717143707275394 Profit 277.1201171875 Loss [1525.0965576171875]\n", + "epsilon:0.001146874504050829 step:2660 episode:133 last_score -8.717143707275394 Profit 304.876220703125 Loss [1571.2283935546875]\n", + "epsilon:0.0010895307788482875 step:2665 episode:134 last_score 75.33311889648435 Profit 0.0 Loss [1076.36474609375]\n", + "epsilon:0.0010895307788482875 step:2670 episode:134 last_score 75.33311889648435 Profit 0.0 Loss [1153.6995849609375]\n", + "epsilon:0.0010895307788482875 step:2675 episode:134 last_score 75.33311889648435 Profit -0.55194091796875 Loss [2575.198974609375]\n", + "epsilon:0.0010895307788482875 step:2680 episode:134 last_score 75.33311889648435 Profit -0.55194091796875 Loss [876.7489013671875]\n", + "epsilon:0.001035054239905873 step:2685 episode:135 last_score -30.334395141601565 Profit 280.864013671875 Loss [2377.732421875]\n", + "epsilon:0.001035054239905873 step:2690 episode:135 last_score -30.334395141601565 Profit 280.864013671875 Loss [1969.3597412109375]\n", + "epsilon:0.001035054239905873 step:2695 episode:135 last_score -30.334395141601565 Profit 280.864013671875 Loss [1536.7637939453125]\n", + "epsilon:0.001035054239905873 step:2700 episode:135 last_score -30.334395141601565 Profit 280.864013671875 Loss [1824.37890625]\n", + "epsilon:0.0009833015279105794 step:2705 episode:136 last_score -92.54824951171881 Profit 0.0 Loss [1390.253173828125]\n", + "epsilon:0.0009833015279105794 step:2710 episode:136 last_score -92.54824951171881 Profit 0.0 Loss [1907.8280029296875]\n", + "epsilon:0.0009833015279105794 step:2715 episode:136 last_score -92.54824951171881 Profit 0.0 Loss [2414.624755859375]\n", + "epsilon:0.0009833015279105794 step:2720 episode:136 last_score -92.54824951171881 Profit 0.0 Loss [987.2946166992188]\n", + "epsilon:0.0009833015279105794 step:2725 episode:137 last_score -843.1960668945314 Profit 0.0 Loss [1070.976806640625]\n", + "epsilon:0.0009833015279105794 step:2730 episode:137 last_score -843.1960668945314 Profit 0.0 Loss [1571.2215576171875]\n", + "epsilon:0.0009833015279105794 step:2735 episode:137 last_score -843.1960668945314 Profit 113.33401489257812 Loss [2413.984619140625]\n", + "epsilon:0.0009833015279105794 step:2740 episode:137 last_score -843.1960668945314 Profit 113.33401489257812 Loss [1012.5181884765625]\n", + "epsilon:0.0009833015279105794 step:2745 episode:138 last_score 34.18773620605468 Profit 0.0 Loss [1148.1363525390625]\n", + "epsilon:0.0009833015279105794 step:2750 episode:138 last_score 34.18773620605468 Profit 0.0 Loss [1323.0927734375]\n", + "epsilon:0.0009833015279105794 step:2755 episode:138 last_score 34.18773620605468 Profit -124.10452270507812 Loss [1572.1912841796875]\n", + "epsilon:0.0009833015279105794 step:2760 episode:138 last_score 34.18773620605468 Profit -124.10452270507812 Loss [1797.91845703125]\n", + "epsilon:0.0009833015279105794 step:2765 episode:139 last_score -184.0582537841797 Profit 0.0 Loss [1298.83349609375]\n", + "epsilon:0.0009833015279105794 step:2770 episode:139 last_score -184.0582537841797 Profit 0.0 Loss [1129.09033203125]\n", + "epsilon:0.0009833015279105794 step:2775 episode:139 last_score -184.0582537841797 Profit 0.0 Loss [1491.28369140625]\n", + "epsilon:0.0009833015279105794 step:2780 episode:139 last_score -184.0582537841797 Profit -107.136962890625 Loss [2533.358642578125]\n", + "epsilon:0.0009833015279105794 step:2785 episode:140 last_score -621.728125 Profit 0.0 Loss [937.3993530273438]\n", + "epsilon:0.0009833015279105794 step:2790 episode:140 last_score -621.728125 Profit 206.9100341796875 Loss [1270.2254638671875]\n", + "epsilon:0.0009833015279105794 step:2795 episode:140 last_score -621.728125 Profit 318.1400146484375 Loss [1641.99609375]\n", + "epsilon:0.0009833015279105794 step:2800 episode:140 last_score -621.728125 Profit 318.1400146484375 Loss [1188.871826171875]\n", + "epsilon:0.0009833015279105794 step:2805 episode:141 last_score 319.1931640625 Profit 0.0 Loss [3156.840087890625]\n", + "epsilon:0.0009833015279105794 step:2810 episode:141 last_score 319.1931640625 Profit 0.0 Loss [1772.11962890625]\n", + "epsilon:0.0009833015279105794 step:2815 episode:141 last_score 319.1931640625 Profit 6.75592041015625 Loss [651.678955078125]\n", + "epsilon:0.0009833015279105794 step:2820 episode:141 last_score 319.1931640625 Profit 6.75592041015625 Loss [2829.39306640625]\n", + "epsilon:0.0009833015279105794 step:2825 episode:142 last_score -37.36776473999023 Profit 131.78399658203125 Loss [1290.314453125]\n", + "epsilon:0.0009833015279105794 step:2830 episode:142 last_score -37.36776473999023 Profit 131.78399658203125 Loss [2458.82275390625]\n", + "epsilon:0.0009833015279105794 step:2835 episode:142 last_score -37.36776473999023 Profit 121.83697509765625 Loss [1580.5211181640625]\n", + "epsilon:0.0009833015279105794 step:2840 episode:142 last_score -37.36776473999023 Profit 133.04193115234375 Loss [2257.62158203125]\n", + "epsilon:0.0009833015279105794 step:2845 episode:143 last_score 78.44485595703127 Profit 0.0 Loss [980.6052856445312]\n", + "epsilon:0.0009833015279105794 step:2850 episode:143 last_score 78.44485595703127 Profit 0.0 Loss [1038.64794921875]\n", + "epsilon:0.0009833015279105794 step:2855 episode:143 last_score 78.44485595703127 Profit 0.0 Loss [1193.1812744140625]\n", + "epsilon:0.0009833015279105794 step:2860 episode:143 last_score 78.44485595703127 Profit 60.476470947265625 Loss [1511.1131591796875]\n", + "epsilon:0.0009833015279105794 step:2865 episode:144 last_score 11.995794067382796 Profit 0.0 Loss [1997.66650390625]\n", + "epsilon:0.0009833015279105794 step:2870 episode:144 last_score 11.995794067382796 Profit 31.02130126953125 Loss [2152.16796875]\n", + "epsilon:0.0009833015279105794 step:2875 episode:144 last_score 11.995794067382796 Profit 31.02130126953125 Loss [1499.0751953125]\n", + "epsilon:0.0009833015279105794 step:2880 episode:144 last_score 11.995794067382796 Profit 35.58061218261719 Loss [1522.0809326171875]\n", + "epsilon:0.0009833015279105794 step:2885 episode:145 last_score 41.09171325683593 Profit 15.148483276367188 Loss [2476.387451171875]\n", + "epsilon:0.0009833015279105794 step:2890 episode:145 last_score 41.09171325683593 Profit 27.799880981445312 Loss [2564.4580078125]\n", + "epsilon:0.0009833015279105794 step:2895 episode:145 last_score 41.09171325683593 Profit 27.799880981445312 Loss [817.4081420898438]\n", + "epsilon:0.0009833015279105794 step:2900 episode:145 last_score 41.09171325683593 Profit 27.799880981445312 Loss [1896.93603515625]\n", + "epsilon:0.0009833015279105794 step:2905 episode:146 last_score 20.88724853515625 Profit 0.0 Loss [938.909423828125]\n", + "epsilon:0.0009833015279105794 step:2910 episode:146 last_score 20.88724853515625 Profit 18.499099731445312 Loss [933.123046875]\n", + "epsilon:0.0009833015279105794 step:2915 episode:146 last_score 20.88724853515625 Profit 18.499099731445312 Loss [1937.63037109375]\n", + "epsilon:0.0009833015279105794 step:2920 episode:146 last_score 20.88724853515625 Profit 18.499099731445312 Loss [1550.6065673828125]\n", + "epsilon:0.0009833015279105794 step:2925 episode:147 last_score -21.84056793212891 Profit 0.0 Loss [1048.7332763671875]\n", + "epsilon:0.0009833015279105794 step:2930 episode:147 last_score -21.84056793212891 Profit 304.40704345703125 Loss [965.127197265625]\n", + "epsilon:0.0009833015279105794 step:2935 episode:147 last_score -21.84056793212891 Profit 304.40704345703125 Loss [467.71368408203125]\n", + "epsilon:0.0009833015279105794 step:2940 episode:147 last_score -21.84056793212891 Profit 304.40704345703125 Loss [2614.6376953125]\n", + "epsilon:0.0009833015279105794 step:2945 episode:148 last_score 376.1661767578125 Profit 0.0 Loss [2548.1298828125]\n", + "epsilon:0.0009833015279105794 step:2950 episode:148 last_score 376.1661767578125 Profit 0.0 Loss [1610.510986328125]\n", + "epsilon:0.0009833015279105794 step:2955 episode:148 last_score 376.1661767578125 Profit 0.0 Loss [2213.456787109375]\n", + "epsilon:0.0009833015279105794 step:2960 episode:148 last_score 376.1661767578125 Profit 0.0 Loss [788.6964111328125]\n", + "epsilon:0.0009833015279105794 step:2965 episode:149 last_score -870.6196044921872 Profit 0.0 Loss [1546.4937744140625]\n", + "epsilon:0.0009833015279105794 step:2970 episode:149 last_score -870.6196044921872 Profit 3.92010498046875 Loss [1564.7884521484375]\n", + "epsilon:0.0009833015279105794 step:2975 episode:149 last_score -870.6196044921872 Profit 14.810630798339844 Loss [1110.8936767578125]\n", + "epsilon:0.0009833015279105794 step:2980 episode:149 last_score -870.6196044921872 Profit 16.333351135253906 Loss [2391.906982421875]\n", + "epsilon:0.0009833015279105794 step:2985 episode:150 last_score 7.388717575073241 Profit 0.0 Loss [2459.706298828125]\n", + "epsilon:0.0009833015279105794 step:2990 episode:150 last_score 7.388717575073241 Profit 0.0 Loss [1554.0919189453125]\n", + "epsilon:0.0009833015279105794 step:2995 episode:150 last_score 7.388717575073241 Profit 0.0 Loss [936.9368896484375]\n", + "epsilon:0.0009833015279105794 step:3000 episode:150 last_score 7.388717575073241 Profit 0.0 Loss [1479.03662109375]\n", + "epsilon:0.0009833015279105794 step:3005 episode:151 last_score -195.5280529785156 Profit 0.0 Loss [462.2049865722656]\n", + "epsilon:0.0009833015279105794 step:3010 episode:151 last_score -195.5280529785156 Profit 0.0 Loss [2655.585693359375]\n", + "epsilon:0.0009833015279105794 step:3015 episode:151 last_score -195.5280529785156 Profit 0.0 Loss [803.3037719726562]\n", + "epsilon:0.0009833015279105794 step:3020 episode:151 last_score -195.5280529785156 Profit 0.0 Loss [722.41845703125]\n", + "epsilon:0.0009833015279105794 step:3025 episode:152 last_score -216.30742797851562 Profit 0.0 Loss [1823.587158203125]\n", + "epsilon:0.0009833015279105794 step:3030 episode:152 last_score -216.30742797851562 Profit 0.0 Loss [1462.7305908203125]\n", + "epsilon:0.0009833015279105794 step:3035 episode:152 last_score -216.30742797851562 Profit 0.0 Loss [1393.6650390625]\n", + "epsilon:0.0009833015279105794 step:3040 episode:152 last_score -216.30742797851562 Profit 0.0 Loss [2884.284423828125]\n", + "epsilon:0.0009833015279105794 step:3045 episode:153 last_score -64.21971313476563 Profit 0.0 Loss [427.4161071777344]\n", + "epsilon:0.0009833015279105794 step:3050 episode:153 last_score -64.21971313476563 Profit 0.0 Loss [2021.009033203125]\n", + "epsilon:0.0009833015279105794 step:3055 episode:153 last_score -64.21971313476563 Profit 0.0 Loss [923.26220703125]\n", + "epsilon:0.0009833015279105794 step:3060 episode:153 last_score -64.21971313476563 Profit 0.0 Loss [1291.798828125]\n", + "epsilon:0.0009833015279105794 step:3065 episode:154 last_score -119.07344848632813 Profit 0.0 Loss [688.4820556640625]\n", + "epsilon:0.0009833015279105794 step:3070 episode:154 last_score -119.07344848632813 Profit 0.0 Loss [1353.88037109375]\n", + "epsilon:0.0009833015279105794 step:3075 episode:154 last_score -119.07344848632813 Profit 0.0 Loss [1177.328857421875]\n", + "epsilon:0.0009833015279105794 step:3080 episode:154 last_score -119.07344848632813 Profit 0.0 Loss [1511.6993408203125]\n", + "epsilon:0.0009833015279105794 step:3085 episode:155 last_score -46.927932434082024 Profit 0.0 Loss [1428.006591796875]\n", + "epsilon:0.0009833015279105794 step:3090 episode:155 last_score -46.927932434082024 Profit 0.0 Loss [2959.628662109375]\n", + "epsilon:0.0009833015279105794 step:3095 episode:155 last_score -46.927932434082024 Profit 0.0 Loss [1315.0166015625]\n", + "epsilon:0.0009833015279105794 step:3100 episode:155 last_score -46.927932434082024 Profit 0.0 Loss [1578.6737060546875]\n", + "epsilon:0.0009833015279105794 step:3105 episode:156 last_score -47.059529876709 Profit 0.0 Loss [1393.9295654296875]\n", + "epsilon:0.0009833015279105794 step:3110 episode:156 last_score -47.059529876709 Profit 0.0 Loss [1634.783935546875]\n", + "epsilon:0.0009833015279105794 step:3115 episode:156 last_score -47.059529876709 Profit 0.0 Loss [1087.6912841796875]\n", + "epsilon:0.0009833015279105794 step:3120 episode:156 last_score -47.059529876709 Profit 0.0 Loss [1960.6268310546875]\n", + "epsilon:0.0009833015279105794 step:3125 episode:157 last_score -47.3542041015625 Profit 0.0 Loss [868.9953002929688]\n", + "epsilon:0.0009833015279105794 step:3130 episode:157 last_score -47.3542041015625 Profit 0.0 Loss [1172.0882568359375]\n", + "epsilon:0.0009833015279105794 step:3135 episode:157 last_score -47.3542041015625 Profit 0.0 Loss [644.2867431640625]\n", + "epsilon:0.0009833015279105794 step:3140 episode:157 last_score -47.3542041015625 Profit 0.0 Loss [1163.821533203125]\n", + "epsilon:0.0009833015279105794 step:3145 episode:158 last_score -23.551043624877934 Profit 0.0 Loss [770.1253662109375]\n", + "epsilon:0.0009833015279105794 step:3150 episode:158 last_score -23.551043624877934 Profit 0.0 Loss [2213.4638671875]\n", + "epsilon:0.0009833015279105794 step:3155 episode:158 last_score -23.551043624877934 Profit 6.0784149169921875 Loss [1347.629638671875]\n", + "epsilon:0.0009833015279105794 step:3160 episode:158 last_score -23.551043624877934 Profit 3.9853363037109375 Loss [733.442138671875]\n", + "epsilon:0.0009833015279105794 step:3165 episode:159 last_score -25.06725357055664 Profit 0.0 Loss [977.4476318359375]\n", + "epsilon:0.0009833015279105794 step:3170 episode:159 last_score -25.06725357055664 Profit 0.0 Loss [1363.9146728515625]\n", + "epsilon:0.0009833015279105794 step:3175 episode:159 last_score -25.06725357055664 Profit 0.0 Loss [1985.9912109375]\n", + "epsilon:0.0009833015279105794 step:3180 episode:159 last_score -25.06725357055664 Profit 0.0 Loss [806.1173706054688]\n", + "epsilon:0.0009833015279105794 step:3185 episode:160 last_score -68.89532165527343 Profit 0.0 Loss [956.28125]\n", + "epsilon:0.0009833015279105794 step:3190 episode:160 last_score -68.89532165527343 Profit 0.0 Loss [2428.45556640625]\n", + "epsilon:0.0009833015279105794 step:3195 episode:160 last_score -68.89532165527343 Profit 0.0 Loss [1873.614990234375]\n", + "epsilon:0.0009833015279105794 step:3200 episode:160 last_score -68.89532165527343 Profit 0.0 Loss [2557.302734375]\n", + "epsilon:0.0009833015279105794 step:3205 episode:161 last_score -45.554698944091804 Profit 0.0 Loss [1126.026611328125]\n", + "epsilon:0.0009833015279105794 step:3210 episode:161 last_score -45.554698944091804 Profit 0.0 Loss [915.9265747070312]\n", + "epsilon:0.0009833015279105794 step:3215 episode:161 last_score -45.554698944091804 Profit 0.0 Loss [1864.0579833984375]\n", + "epsilon:0.0009833015279105794 step:3220 episode:161 last_score -45.554698944091804 Profit 0.0 Loss [827.630859375]\n", + "epsilon:0.0009833015279105794 step:3225 episode:162 last_score -119.73573822021483 Profit 0.0 Loss [1321.2332763671875]\n", + "epsilon:0.0009833015279105794 step:3230 episode:162 last_score -119.73573822021483 Profit 0.0 Loss [819.3440551757812]\n", + "epsilon:0.0009833015279105794 step:3235 episode:162 last_score -119.73573822021483 Profit 0.0 Loss [2142.043212890625]\n", + "epsilon:0.0009833015279105794 step:3240 episode:162 last_score -119.73573822021483 Profit 0.0 Loss [1386.3031005859375]\n", + "epsilon:0.0009833015279105794 step:3245 episode:163 last_score -98.92160949707034 Profit 0.0 Loss [1246.4749755859375]\n", + "epsilon:0.0009833015279105794 step:3250 episode:163 last_score -98.92160949707034 Profit 0.0 Loss [923.5106201171875]\n", + "epsilon:0.0009833015279105794 step:3255 episode:163 last_score -98.92160949707034 Profit 0.0 Loss [1878.610595703125]\n", + "epsilon:0.0009833015279105794 step:3260 episode:163 last_score -98.92160949707034 Profit 0.0 Loss [837.3643798828125]\n", + "epsilon:0.0009833015279105794 step:3265 episode:164 last_score -71.93179382324219 Profit 0.0 Loss [1165.5230712890625]\n", + "epsilon:0.0009833015279105794 step:3270 episode:164 last_score -71.93179382324219 Profit 0.0 Loss [1475.082763671875]\n", + "epsilon:0.0009833015279105794 step:3275 episode:164 last_score -71.93179382324219 Profit 0.0 Loss [1671.247802734375]\n", + "epsilon:0.0009833015279105794 step:3280 episode:164 last_score -71.93179382324219 Profit 0.0 Loss [951.854248046875]\n", + "epsilon:0.0009833015279105794 step:3285 episode:165 last_score -741.08478515625 Profit 0.0 Loss [1688.7342529296875]\n", + "epsilon:0.0009833015279105794 step:3290 episode:165 last_score -741.08478515625 Profit 0.0 Loss [1692.3045654296875]\n", + "epsilon:0.0009833015279105794 step:3295 episode:165 last_score -741.08478515625 Profit 0.0 Loss [201.5704345703125]\n", + "epsilon:0.0009833015279105794 step:3300 episode:165 last_score -741.08478515625 Profit 0.0 Loss [1872.5462646484375]\n", + "epsilon:0.0009833015279105794 step:3305 episode:166 last_score -25.15708892822266 Profit 0.0 Loss [796.7220458984375]\n", + "epsilon:0.0009833015279105794 step:3310 episode:166 last_score -25.15708892822266 Profit 0.0 Loss [1385.75244140625]\n", + "epsilon:0.0009833015279105794 step:3315 episode:166 last_score -25.15708892822266 Profit 0.0 Loss [707.4249877929688]\n", + "epsilon:0.0009833015279105794 step:3320 episode:166 last_score -25.15708892822266 Profit 0.0 Loss [1482.4710693359375]\n", + "epsilon:0.0009833015279105794 step:3325 episode:167 last_score -61.01525360107422 Profit 0.0 Loss [1246.08935546875]\n", + "epsilon:0.0009833015279105794 step:3330 episode:167 last_score -61.01525360107422 Profit 0.0 Loss [2982.2587890625]\n", + "epsilon:0.0009833015279105794 step:3335 episode:167 last_score -61.01525360107422 Profit 0.0 Loss [3297.867431640625]\n", + "epsilon:0.0009833015279105794 step:3340 episode:167 last_score -61.01525360107422 Profit 0.0 Loss [1679.9342041015625]\n", + "epsilon:0.0009833015279105794 step:3345 episode:168 last_score -31.969149017333983 Profit 0.0 Loss [773.4898681640625]\n", + "epsilon:0.0009833015279105794 step:3350 episode:168 last_score -31.969149017333983 Profit 0.0 Loss [1226.27490234375]\n", + "epsilon:0.0009833015279105794 step:3355 episode:168 last_score -31.969149017333983 Profit 0.0 Loss [1730.2650146484375]\n", + "epsilon:0.0009833015279105794 step:3360 episode:168 last_score -31.969149017333983 Profit 0.0 Loss [995.6709594726562]\n", + "epsilon:0.0009833015279105794 step:3365 episode:169 last_score -102.89620605468751 Profit 0.0 Loss [1272.2244873046875]\n", + "epsilon:0.0009833015279105794 step:3370 episode:169 last_score -102.89620605468751 Profit 0.0 Loss [880.7820434570312]\n", + "epsilon:0.0009833015279105794 step:3375 episode:169 last_score -102.89620605468751 Profit 0.0 Loss [570.76123046875]\n", + "epsilon:0.0009833015279105794 step:3380 episode:169 last_score -102.89620605468751 Profit 0.0 Loss [1694.5770263671875]\n", + "epsilon:0.0009833015279105794 step:3385 episode:170 last_score -77.36392181396484 Profit 0.0 Loss [1515.8447265625]\n", + "epsilon:0.0009833015279105794 step:3390 episode:170 last_score -77.36392181396484 Profit 0.0 Loss [1126.4822998046875]\n", + "epsilon:0.0009833015279105794 step:3395 episode:170 last_score -77.36392181396484 Profit 0.0 Loss [2807.441162109375]\n", + "epsilon:0.0009833015279105794 step:3400 episode:170 last_score -77.36392181396484 Profit 0.0 Loss [1065.90234375]\n", + "epsilon:0.0009833015279105794 step:3405 episode:171 last_score -108.4504803466797 Profit 0.0 Loss [819.3470458984375]\n", + "epsilon:0.0009833015279105794 step:3410 episode:171 last_score -108.4504803466797 Profit 0.0 Loss [1760.4150390625]\n", + "epsilon:0.0009833015279105794 step:3415 episode:171 last_score -108.4504803466797 Profit 0.0 Loss [783.933349609375]\n", + "epsilon:0.0009833015279105794 step:3420 episode:171 last_score -108.4504803466797 Profit 0.0 Loss [1364.3447265625]\n", + "epsilon:0.0009833015279105794 step:3425 episode:172 last_score -22.340631408691408 Profit 0.0 Loss [1789.9842529296875]\n", + "epsilon:0.0009833015279105794 step:3430 episode:172 last_score -22.340631408691408 Profit 0.0 Loss [2046.0306396484375]\n", + "epsilon:0.0009833015279105794 step:3435 episode:172 last_score -22.340631408691408 Profit 0.0 Loss [870.2320556640625]\n", + "epsilon:0.0009833015279105794 step:3440 episode:172 last_score -22.340631408691408 Profit 0.0 Loss [1410.1884765625]\n", + "epsilon:0.0009833015279105794 step:3445 episode:173 last_score -114.47063568115236 Profit 0.0 Loss [1427.7275390625]\n", + "epsilon:0.0009833015279105794 step:3450 episode:173 last_score -114.47063568115236 Profit 0.0 Loss [2515.426025390625]\n", + "epsilon:0.0009833015279105794 step:3455 episode:173 last_score -114.47063568115236 Profit 0.0 Loss [3118.460693359375]\n", + "epsilon:0.0009833015279105794 step:3460 episode:173 last_score -114.47063568115236 Profit 0.0 Loss [973.3200073242188]\n", + "epsilon:0.0009833015279105794 step:3465 episode:174 last_score -25.43018295288086 Profit -0.9351043701171875 Loss [1806.2237548828125]\n", + "epsilon:0.0009833015279105794 step:3470 episode:174 last_score -25.43018295288086 Profit 5.0761871337890625 Loss [2893.22509765625]\n", + "epsilon:0.0009833015279105794 step:3475 episode:174 last_score -25.43018295288086 Profit 10.495063781738281 Loss [766.911376953125]\n", + "epsilon:0.0009833015279105794 step:3480 episode:174 last_score -25.43018295288086 Profit 10.495063781738281 Loss [1302.06982421875]\n", + "epsilon:0.0009833015279105794 step:3485 episode:175 last_score -4.16515983581543 Profit 0.0 Loss [833.408203125]\n", + "epsilon:0.0009833015279105794 step:3490 episode:175 last_score -4.16515983581543 Profit 0.0 Loss [449.4400634765625]\n", + "epsilon:0.0009833015279105794 step:3495 episode:175 last_score -4.16515983581543 Profit 1030.201171875 Loss [1550.9000244140625]\n", + "epsilon:0.0009833015279105794 step:3500 episode:175 last_score -4.16515983581543 Profit 952.535888671875 Loss [1768.2225341796875]\n", + "epsilon:0.0009833015279105794 step:3505 episode:176 last_score 61.165756835937486 Profit 0.0 Loss [1436.4652099609375]\n", + "epsilon:0.0009833015279105794 step:3510 episode:176 last_score 61.165756835937486 Profit 130.072021484375 Loss [1893.3896484375]\n", + "epsilon:0.0009833015279105794 step:3515 episode:176 last_score 61.165756835937486 Profit 130.072021484375 Loss [987.00390625]\n", + "epsilon:0.0009833015279105794 step:3520 episode:176 last_score 61.165756835937486 Profit 261.81298828125 Loss [2542.39306640625]\n", + "epsilon:0.0009833015279105794 step:3525 episode:177 last_score 175.4292498779297 Profit 0.0 Loss [519.8519897460938]\n", + "epsilon:0.0009833015279105794 step:3530 episode:177 last_score 175.4292498779297 Profit 0.0 Loss [871.42626953125]\n", + "epsilon:0.0009833015279105794 step:3535 episode:177 last_score 175.4292498779297 Profit 0.0 Loss [1368.4681396484375]\n", + "epsilon:0.0009833015279105794 step:3540 episode:177 last_score 175.4292498779297 Profit 0.0 Loss [1452.440673828125]\n", + "epsilon:0.0009833015279105794 step:3545 episode:178 last_score -626.3294042968749 Profit 0.0 Loss [2761.460205078125]\n", + "epsilon:0.0009833015279105794 step:3550 episode:178 last_score -626.3294042968749 Profit 0.0 Loss [2839.697265625]\n", + "epsilon:0.0009833015279105794 step:3555 episode:178 last_score -626.3294042968749 Profit 0.0 Loss [973.74755859375]\n", + "epsilon:0.0009833015279105794 step:3560 episode:178 last_score -626.3294042968749 Profit 0.0 Loss [940.7178955078125]\n", + "epsilon:0.0009833015279105794 step:3565 episode:179 last_score -23.185561370849612 Profit 0.0 Loss [389.8953552246094]\n", + "epsilon:0.0009833015279105794 step:3570 episode:179 last_score -23.185561370849612 Profit 15.23834228515625 Loss [2162.615966796875]\n", + "epsilon:0.0009833015279105794 step:3575 episode:179 last_score -23.185561370849612 Profit 11.071807861328125 Loss [2485.5693359375]\n", + "epsilon:0.0009833015279105794 step:3580 episode:179 last_score -23.185561370849612 Profit 11.071807861328125 Loss [1239.6597900390625]\n", + "epsilon:0.0009833015279105794 step:3585 episode:180 last_score -26.060828399658206 Profit 0.0 Loss [2344.129150390625]\n", + "epsilon:0.0009833015279105794 step:3590 episode:180 last_score -26.060828399658206 Profit 0.0 Loss [488.929443359375]\n", + "epsilon:0.0009833015279105794 step:3595 episode:180 last_score -26.060828399658206 Profit 0.0 Loss [1299.2464599609375]\n", + "epsilon:0.0009833015279105794 step:3600 episode:180 last_score -26.060828399658206 Profit 0.0 Loss [4580.5146484375]\n", + "epsilon:0.0009833015279105794 step:3605 episode:181 last_score -108.4504803466797 Profit 15.38134765625 Loss [3369.233642578125]\n", + "epsilon:0.0009833015279105794 step:3610 episode:181 last_score -108.4504803466797 Profit 15.38134765625 Loss [3631.0888671875]\n", + "epsilon:0.0009833015279105794 step:3615 episode:181 last_score -108.4504803466797 Profit -185.912353515625 Loss [955.4411010742188]\n", + "epsilon:0.0009833015279105794 step:3620 episode:181 last_score -108.4504803466797 Profit -185.912353515625 Loss [283.9996032714844]\n", + "epsilon:0.0009833015279105794 step:3625 episode:182 last_score -926.8890100097656 Profit 0.0 Loss [2299.69921875]\n", + "epsilon:0.0009833015279105794 step:3630 episode:182 last_score -926.8890100097656 Profit 18.399505615234375 Loss [1735.534423828125]\n", + "epsilon:0.0009833015279105794 step:3635 episode:182 last_score -926.8890100097656 Profit 44.43406677246094 Loss [2619.354736328125]\n", + "epsilon:0.0009833015279105794 step:3640 episode:182 last_score -926.8890100097656 Profit 44.43406677246094 Loss [1172.8907470703125]\n", + "epsilon:0.0009833015279105794 step:3645 episode:183 last_score 8.663939971923824 Profit 16.576171875 Loss [1191.9267578125]\n", + "epsilon:0.0009833015279105794 step:3650 episode:183 last_score 8.663939971923824 Profit 83.340576171875 Loss [350.0651550292969]\n", + "epsilon:0.0009833015279105794 step:3655 episode:183 last_score 8.663939971923824 Profit 83.340576171875 Loss [1312.949951171875]\n", + "epsilon:0.0009833015279105794 step:3660 episode:183 last_score 8.663939971923824 Profit 160.323486328125 Loss [753.873291015625]\n", + "epsilon:0.0009833015279105794 step:3665 episode:184 last_score -323.92501953125 Profit 0.0 Loss [456.517578125]\n", + "epsilon:0.0009833015279105794 step:3670 episode:184 last_score -323.92501953125 Profit 0.0 Loss [2093.879638671875]\n", + "epsilon:0.0009833015279105794 step:3675 episode:184 last_score -323.92501953125 Profit 113.33401489257812 Loss [1920.08056640625]\n", + "epsilon:0.0009833015279105794 step:3680 episode:184 last_score -323.92501953125 Profit 113.33401489257812 Loss [1049.5899658203125]\n", + "epsilon:0.0009833015279105794 step:3685 episode:185 last_score 34.18773620605468 Profit 0.0 Loss [1210.40673828125]\n", + "epsilon:0.0009833015279105794 step:3690 episode:185 last_score 34.18773620605468 Profit 0.0 Loss [1205.7305908203125]\n", + "epsilon:0.0009833015279105794 step:3695 episode:185 last_score 34.18773620605468 Profit 0.0 Loss [1082.6578369140625]\n", + "epsilon:0.0009833015279105794 step:3700 episode:185 last_score 34.18773620605468 Profit 0.0 Loss [1384.9659423828125]\n", + "epsilon:0.0009833015279105794 step:3705 episode:186 last_score -44.912899322509766 Profit 0.0 Loss [1419.910888671875]\n", + "epsilon:0.0009833015279105794 step:3710 episode:186 last_score -44.912899322509766 Profit 0.0 Loss [1782.1138916015625]\n", + "epsilon:0.0009833015279105794 step:3715 episode:186 last_score -44.912899322509766 Profit 21.991943359375 Loss [1665.024658203125]\n", + "epsilon:0.0009833015279105794 step:3720 episode:186 last_score -44.912899322509766 Profit 21.991943359375 Loss [1392.899169921875]\n", + "epsilon:0.0009833015279105794 step:3725 episode:187 last_score -33.287355499267576 Profit 0.0 Loss [727.2210693359375]\n", + "epsilon:0.0009833015279105794 step:3730 episode:187 last_score -33.287355499267576 Profit 44.9530029296875 Loss [1875.5279541015625]\n", + "epsilon:0.0009833015279105794 step:3735 episode:187 last_score -33.287355499267576 Profit 44.9530029296875 Loss [1799.68408203125]\n", + "epsilon:0.0009833015279105794 step:3740 episode:187 last_score -33.287355499267576 Profit 71.54302978515625 Loss [2820.322509765625]\n", + "epsilon:0.0009833015279105794 step:3745 episode:188 last_score 11.50945831298828 Profit 0.0 Loss [515.1668090820312]\n", + "epsilon:0.0009833015279105794 step:3750 episode:188 last_score 11.50945831298828 Profit 0.0 Loss [1942.4859619140625]\n", + "epsilon:0.0009833015279105794 step:3755 episode:188 last_score 11.50945831298828 Profit 0.0 Loss [898.8323974609375]\n", + "epsilon:0.0009833015279105794 step:3760 episode:188 last_score 11.50945831298828 Profit 0.0 Loss [731.3735961914062]\n", + "epsilon:0.0009833015279105794 step:3765 episode:189 last_score -626.3294042968749 Profit 0.0 Loss [708.50439453125]\n", + "epsilon:0.0009833015279105794 step:3770 episode:189 last_score -626.3294042968749 Profit 0.0 Loss [1919.2349853515625]\n", + "epsilon:0.0009833015279105794 step:3775 episode:189 last_score -626.3294042968749 Profit 0.0 Loss [1583.2216796875]\n", + "epsilon:0.0009833015279105794 step:3780 episode:189 last_score -626.3294042968749 Profit 0.0 Loss [986.3406372070312]\n", + "epsilon:0.0009833015279105794 step:3785 episode:190 last_score -3.6635163879394543 Profit 0.0 Loss [499.8544616699219]\n", + "epsilon:0.0009833015279105794 step:3790 episode:190 last_score -3.6635163879394543 Profit 8.078536987304688 Loss [451.3110046386719]\n", + "epsilon:0.0009833015279105794 step:3795 episode:190 last_score -3.6635163879394543 Profit 10.773849487304688 Loss [1040.19677734375]\n", + "epsilon:0.0009833015279105794 step:3800 episode:190 last_score -3.6635163879394543 Profit 10.773849487304688 Loss [1025.8299560546875]\n", + "epsilon:0.0009833015279105794 step:3805 episode:191 last_score -15.772071075439452 Profit 0.0 Loss [2015.3045654296875]\n", + "epsilon:0.0009833015279105794 step:3810 episode:191 last_score -15.772071075439452 Profit 0.0 Loss [442.6893615722656]\n", + "epsilon:0.0009833015279105794 step:3815 episode:191 last_score -15.772071075439452 Profit 2.7790069580078125 Loss [1362.265625]\n", + "epsilon:0.0009833015279105794 step:3820 episode:191 last_score -15.772071075439452 Profit 2.7790069580078125 Loss [1190.8726806640625]\n", + "epsilon:0.0009833015279105794 step:3825 episode:192 last_score -24.724400405883788 Profit 0.0 Loss [1361.8487548828125]\n", + "epsilon:0.0009833015279105794 step:3830 episode:192 last_score -24.724400405883788 Profit 0.0 Loss [2570.5400390625]\n", + "epsilon:0.0009833015279105794 step:3835 episode:192 last_score -24.724400405883788 Profit 0.0 Loss [949.3908081054688]\n", + "epsilon:0.0009833015279105794 step:3840 episode:192 last_score -24.724400405883788 Profit 0.0 Loss [721.8858032226562]\n", + "epsilon:0.0009833015279105794 step:3845 episode:193 last_score -97.38220947265629 Profit 0.0 Loss [610.1454467773438]\n", + "epsilon:0.0009833015279105794 step:3850 episode:193 last_score -97.38220947265629 Profit 0.0 Loss [889.7943725585938]\n", + "epsilon:0.0009833015279105794 step:3855 episode:193 last_score -97.38220947265629 Profit 0.0 Loss [1400.8831787109375]\n", + "epsilon:0.0009833015279105794 step:3860 episode:193 last_score -97.38220947265629 Profit 0.0 Loss [2403.9189453125]\n", + "epsilon:0.0009833015279105794 step:3865 episode:194 last_score -180.23018554687502 Profit 0.0 Loss [2110.900390625]\n", + "epsilon:0.0009833015279105794 step:3870 episode:194 last_score -180.23018554687502 Profit 0.0 Loss [584.5018920898438]\n", + "epsilon:0.0009833015279105794 step:3875 episode:194 last_score -180.23018554687502 Profit 0.0 Loss [1015.4367065429688]\n", + "epsilon:0.0009833015279105794 step:3880 episode:194 last_score -180.23018554687502 Profit 0.0 Loss [298.41241455078125]\n", + "epsilon:0.0009833015279105794 step:3885 episode:195 last_score -23.84338981628418 Profit 0.0 Loss [2818.999267578125]\n", + "epsilon:0.0009833015279105794 step:3890 episode:195 last_score -23.84338981628418 Profit 0.0 Loss [605.7398071289062]\n", + "epsilon:0.0009833015279105794 step:3895 episode:195 last_score -23.84338981628418 Profit 0.0 Loss [1396.8662109375]\n", + "epsilon:0.0009833015279105794 step:3900 episode:195 last_score -23.84338981628418 Profit 0.0 Loss [2387.1630859375]\n", + "epsilon:0.0009833015279105794 step:3905 episode:196 last_score -328.0068115234375 Profit 0.0 Loss [706.7136840820312]\n", + "epsilon:0.0009833015279105794 step:3910 episode:196 last_score -328.0068115234375 Profit 0.0 Loss [1599.3648681640625]\n", + "epsilon:0.0009833015279105794 step:3915 episode:196 last_score -328.0068115234375 Profit 0.0 Loss [1705.793701171875]\n", + "epsilon:0.0009833015279105794 step:3920 episode:196 last_score -328.0068115234375 Profit 0.0 Loss [1475.6925048828125]\n", + "epsilon:0.0009833015279105794 step:3925 episode:197 last_score -76.94262268066407 Profit 0.0 Loss [1138.168701171875]\n", + "epsilon:0.0009833015279105794 step:3930 episode:197 last_score -76.94262268066407 Profit 0.0 Loss [1329.44091796875]\n", + "epsilon:0.0009833015279105794 step:3935 episode:197 last_score -76.94262268066407 Profit 0.0 Loss [1499.3812255859375]\n", + "epsilon:0.0009833015279105794 step:3940 episode:197 last_score -76.94262268066407 Profit 0.0 Loss [1014.9834594726562]\n", + "epsilon:0.0009833015279105794 step:3945 episode:198 last_score -71.27619201660156 Profit 0.0 Loss [897.04296875]\n", + "epsilon:0.0009833015279105794 step:3950 episode:198 last_score -71.27619201660156 Profit 0.0 Loss [635.7252197265625]\n", + "epsilon:0.0009833015279105794 step:3955 episode:198 last_score -71.27619201660156 Profit 0.0 Loss [1071.00830078125]\n", + "epsilon:0.0009833015279105794 step:3960 episode:198 last_score -71.27619201660156 Profit 0.0 Loss [669.4835815429688]\n", + "epsilon:0.0009833015279105794 step:3965 episode:199 last_score -24.641188888549802 Profit 0.0 Loss [1483.2806396484375]\n", + "epsilon:0.0009833015279105794 step:3970 episode:199 last_score -24.641188888549802 Profit 0.0 Loss [1570.9248046875]\n", + "epsilon:0.0009833015279105794 step:3975 episode:199 last_score -24.641188888549802 Profit 0.0 Loss [290.8641662597656]\n", + "epsilon:0.0009833015279105794 step:3980 episode:199 last_score -24.641188888549802 Profit 0.0 Loss [1464.87939453125]\n", + "epsilon:0.0009833015279105794 step:3985 episode:200 last_score -36.51565620422363 Profit 0.0 Loss [660.089599609375]\n", + "epsilon:0.0009833015279105794 step:3990 episode:200 last_score -36.51565620422363 Profit 0.0 Loss [493.9936828613281]\n", + "epsilon:0.0009833015279105794 step:3995 episode:200 last_score -36.51565620422363 Profit 0.0 Loss [666.6867065429688]\n", + "epsilon:0.0009833015279105794 step:4000 episode:200 last_score -36.51565620422363 Profit 0.0 Loss [2987.23095703125]\n", + "epsilon:0.0009833015279105794 step:4005 episode:201 last_score -27.79757217407227 Profit 0.0 Loss [1220.3048095703125]\n", + "epsilon:0.0009833015279105794 step:4010 episode:201 last_score -27.79757217407227 Profit 0.0 Loss [712.5901489257812]\n", + "epsilon:0.0009833015279105794 step:4015 episode:201 last_score -27.79757217407227 Profit 0.0 Loss [1589.474365234375]\n", + "epsilon:0.0009833015279105794 step:4020 episode:201 last_score -27.79757217407227 Profit 0.0 Loss [1262.9285888671875]\n", + "epsilon:0.0009833015279105794 step:4025 episode:202 last_score -284.0790466308594 Profit 0.0 Loss [1167.3065185546875]\n", + "epsilon:0.0009833015279105794 step:4030 episode:202 last_score -284.0790466308594 Profit 0.0 Loss [790.7189331054688]\n", + "epsilon:0.0009833015279105794 step:4035 episode:202 last_score -284.0790466308594 Profit 0.0 Loss [323.2065734863281]\n", + "epsilon:0.0009833015279105794 step:4040 episode:202 last_score -284.0790466308594 Profit 0.0 Loss [283.53076171875]\n", + "epsilon:0.0009833015279105794 step:4045 episode:203 last_score -30.55678421020508 Profit 0.0 Loss [665.834228515625]\n", + "epsilon:0.0009833015279105794 step:4050 episode:203 last_score -30.55678421020508 Profit 0.0 Loss [806.1527099609375]\n", + "epsilon:0.0009833015279105794 step:4055 episode:203 last_score -30.55678421020508 Profit 0.0 Loss [1503.5628662109375]\n", + "epsilon:0.0009833015279105794 step:4060 episode:203 last_score -30.55678421020508 Profit 0.0 Loss [1828.1807861328125]\n", + "epsilon:0.0009833015279105794 step:4065 episode:204 last_score -33.66307800292969 Profit 0.0 Loss [1025.4656982421875]\n", + "epsilon:0.0009833015279105794 step:4070 episode:204 last_score -33.66307800292969 Profit 0.0 Loss [1248.9927978515625]\n", + "epsilon:0.0009833015279105794 step:4075 episode:204 last_score -33.66307800292969 Profit 0.0 Loss [1335.4462890625]\n", + "epsilon:0.0009833015279105794 step:4080 episode:204 last_score -33.66307800292969 Profit 0.0 Loss [2516.464111328125]\n", + "epsilon:0.0009833015279105794 step:4085 episode:205 last_score -370.8452978515625 Profit 0.0 Loss [1526.8868408203125]\n", + "epsilon:0.0009833015279105794 step:4090 episode:205 last_score -370.8452978515625 Profit 0.0 Loss [2631.906494140625]\n", + "epsilon:0.0009833015279105794 step:4095 episode:205 last_score -370.8452978515625 Profit 0.0 Loss [920.5493774414062]\n", + "epsilon:0.0009833015279105794 step:4100 episode:205 last_score -370.8452978515625 Profit 0.0 Loss [255.1868896484375]\n", + "epsilon:0.0009833015279105794 step:4105 episode:206 last_score -34.36012619018555 Profit 0.0 Loss [390.2084045410156]\n", + "epsilon:0.0009833015279105794 step:4110 episode:206 last_score -34.36012619018555 Profit 0.0 Loss [212.8878936767578]\n", + "epsilon:0.0009833015279105794 step:4115 episode:206 last_score -34.36012619018555 Profit 0.0 Loss [1303.5198974609375]\n", + "epsilon:0.0009833015279105794 step:4120 episode:206 last_score -34.36012619018555 Profit 0.0 Loss [1039.0791015625]\n", + "epsilon:0.0009833015279105794 step:4125 episode:207 last_score -255.28304931640628 Profit 0.0 Loss [1042.0391845703125]\n", + "epsilon:0.0009833015279105794 step:4130 episode:207 last_score -255.28304931640628 Profit 0.0 Loss [1615.2091064453125]\n", + "epsilon:0.0009833015279105794 step:4135 episode:207 last_score -255.28304931640628 Profit 0.0 Loss [1580.4412841796875]\n", + "epsilon:0.0009833015279105794 step:4140 episode:207 last_score -255.28304931640628 Profit 0.0 Loss [407.425537109375]\n", + "epsilon:0.0009833015279105794 step:4145 episode:208 last_score -56.84000534057617 Profit 0.0 Loss [647.0835571289062]\n", + "epsilon:0.0009833015279105794 step:4150 episode:208 last_score -56.84000534057617 Profit 0.0 Loss [1838.9443359375]\n", + "epsilon:0.0009833015279105794 step:4155 episode:208 last_score -56.84000534057617 Profit 0.0 Loss [2053.5498046875]\n", + "epsilon:0.0009833015279105794 step:4160 episode:208 last_score -56.84000534057617 Profit 0.0 Loss [1128.0020751953125]\n", + "epsilon:0.0009833015279105794 step:4165 episode:209 last_score -179.05820678710938 Profit 0.0 Loss [725.5518798828125]\n", + "epsilon:0.0009833015279105794 step:4170 episode:209 last_score -179.05820678710938 Profit 0.0 Loss [536.0711059570312]\n", + "epsilon:0.0009833015279105794 step:4175 episode:209 last_score -179.05820678710938 Profit 0.0 Loss [1061.1337890625]\n", + "epsilon:0.0009833015279105794 step:4180 episode:209 last_score -179.05820678710938 Profit 0.0 Loss [2224.615234375]\n", + "epsilon:0.0009833015279105794 step:4185 episode:210 last_score -76.29304626464844 Profit 0.0 Loss [1836.88671875]\n", + "epsilon:0.0009833015279105794 step:4190 episode:210 last_score -76.29304626464844 Profit 0.0 Loss [747.2034301757812]\n", + "epsilon:0.0009833015279105794 step:4195 episode:210 last_score -76.29304626464844 Profit 0.0 Loss [718.41015625]\n", + "epsilon:0.0009833015279105794 step:4200 episode:210 last_score -76.29304626464844 Profit 0.0 Loss [1324.18017578125]\n", + "epsilon:0.0009833015279105794 step:4205 episode:211 last_score -195.33145019531256 Profit 0.0 Loss [1953.4581298828125]\n", + "epsilon:0.0009833015279105794 step:4210 episode:211 last_score -195.33145019531256 Profit 0.0 Loss [1180.9970703125]\n", + "epsilon:0.0009833015279105794 step:4215 episode:211 last_score -195.33145019531256 Profit 0.0 Loss [1718.2080078125]\n", + "epsilon:0.0009833015279105794 step:4220 episode:211 last_score -195.33145019531256 Profit 0.0 Loss [331.1330871582031]\n", + "epsilon:0.0009833015279105794 step:4225 episode:212 last_score -33.10854705810547 Profit 0.0 Loss [1360.659423828125]\n", + "epsilon:0.0009833015279105794 step:4230 episode:212 last_score -33.10854705810547 Profit 0.0 Loss [454.1634521484375]\n", + "epsilon:0.0009833015279105794 step:4235 episode:212 last_score -33.10854705810547 Profit 0.0 Loss [772.36669921875]\n", + "epsilon:0.0009833015279105794 step:4240 episode:212 last_score -33.10854705810547 Profit 0.0 Loss [765.587890625]\n", + "epsilon:0.0009833015279105794 step:4245 episode:213 last_score -476.35522216796875 Profit 0.0 Loss [622.3486328125]\n", + "epsilon:0.0009833015279105794 step:4250 episode:213 last_score -476.35522216796875 Profit 0.0 Loss [672.2705688476562]\n", + "epsilon:0.0009833015279105794 step:4255 episode:213 last_score -476.35522216796875 Profit 0.0 Loss [1258.33935546875]\n", + "epsilon:0.0009833015279105794 step:4260 episode:213 last_score -476.35522216796875 Profit 0.0 Loss [577.6488037109375]\n", + "epsilon:0.0009833015279105794 step:4265 episode:214 last_score -43.76183410644532 Profit 0.0 Loss [257.81024169921875]\n", + "epsilon:0.0009833015279105794 step:4270 episode:214 last_score -43.76183410644532 Profit 0.0 Loss [792.868408203125]\n", + "epsilon:0.0009833015279105794 step:4275 episode:214 last_score -43.76183410644532 Profit 0.0 Loss [1037.0535888671875]\n", + "epsilon:0.0009833015279105794 step:4280 episode:214 last_score -43.76183410644532 Profit 0.0 Loss [2450.586669921875]\n", + "epsilon:0.0009833015279105794 step:4285 episode:215 last_score -798.3956860351562 Profit 0.0 Loss [678.713623046875]\n", + "epsilon:0.0009833015279105794 step:4290 episode:215 last_score -798.3956860351562 Profit 0.0 Loss [922.836669921875]\n", + "epsilon:0.0009833015279105794 step:4295 episode:215 last_score -798.3956860351562 Profit 0.0 Loss [848.0653076171875]\n", + "epsilon:0.0009833015279105794 step:4300 episode:215 last_score -798.3956860351562 Profit 0.0 Loss [513.940673828125]\n", + "epsilon:0.0009833015279105794 step:4305 episode:216 last_score -49.188933105468756 Profit 0.0 Loss [709.1558837890625]\n", + "epsilon:0.0009833015279105794 step:4310 episode:216 last_score -49.188933105468756 Profit 0.0 Loss [762.41845703125]\n", + "epsilon:0.0009833015279105794 step:4315 episode:216 last_score -49.188933105468756 Profit 0.0 Loss [1127.733154296875]\n", + "epsilon:0.0009833015279105794 step:4320 episode:216 last_score -49.188933105468756 Profit 0.0 Loss [957.90185546875]\n", + "epsilon:0.0009833015279105794 step:4325 episode:217 last_score -27.79757217407227 Profit 0.0 Loss [1038.841064453125]\n", + "epsilon:0.0009833015279105794 step:4330 episode:217 last_score -27.79757217407227 Profit 0.0 Loss [2293.404052734375]\n", + "epsilon:0.0009833015279105794 step:4335 episode:217 last_score -27.79757217407227 Profit 0.0 Loss [881.8124389648438]\n", + "epsilon:0.0009833015279105794 step:4340 episode:217 last_score -27.79757217407227 Profit 0.0 Loss [1909.7308349609375]\n", + "epsilon:0.0009833015279105794 step:4345 episode:218 last_score -26.993847579956057 Profit 0.0 Loss [1704.3785400390625]\n", + "epsilon:0.0009833015279105794 step:4350 episode:218 last_score -26.993847579956057 Profit 0.0 Loss [813.6861572265625]\n", + "epsilon:0.0009833015279105794 step:4355 episode:218 last_score -26.993847579956057 Profit 0.0 Loss [1123.7308349609375]\n", + "epsilon:0.0009833015279105794 step:4360 episode:218 last_score -26.993847579956057 Profit 0.0 Loss [1046.5499267578125]\n", + "epsilon:0.0009833015279105794 step:4365 episode:219 last_score -380.45063476562495 Profit 0.0 Loss [1299.434326171875]\n", + "epsilon:0.0009833015279105794 step:4370 episode:219 last_score -380.45063476562495 Profit 0.0 Loss [793.170654296875]\n", + "epsilon:0.0009833015279105794 step:4375 episode:219 last_score -380.45063476562495 Profit 0.0 Loss [1008.7259521484375]\n", + "epsilon:0.0009833015279105794 step:4380 episode:219 last_score -380.45063476562495 Profit 0.0 Loss [1272.0152587890625]\n", + "epsilon:0.0009833015279105794 step:4385 episode:220 last_score -179.05820678710938 Profit 0.0 Loss [1204.5994873046875]\n", + "epsilon:0.0009833015279105794 step:4390 episode:220 last_score -179.05820678710938 Profit 0.0 Loss [2227.703857421875]\n", + "epsilon:0.0009833015279105794 step:4395 episode:220 last_score -179.05820678710938 Profit 0.0 Loss [797.5150756835938]\n", + "epsilon:0.0009833015279105794 step:4400 episode:220 last_score -179.05820678710938 Profit 0.0 Loss [1031.9117431640625]\n", + "epsilon:0.0009833015279105794 step:4405 episode:221 last_score -359.7231848144532 Profit 0.0 Loss [1150.0462646484375]\n", + "epsilon:0.0009833015279105794 step:4410 episode:221 last_score -359.7231848144532 Profit 0.0 Loss [3183.93310546875]\n", + "epsilon:0.0009833015279105794 step:4415 episode:221 last_score -359.7231848144532 Profit 0.0 Loss [831.5342407226562]\n", + "epsilon:0.0009833015279105794 step:4420 episode:221 last_score -359.7231848144532 Profit 0.0 Loss [518.8583374023438]\n", + "epsilon:0.0009833015279105794 step:4425 episode:222 last_score -38.87445205688477 Profit 0.0 Loss [728.28125]\n", + "epsilon:0.0009833015279105794 step:4430 episode:222 last_score -38.87445205688477 Profit 0.0 Loss [1924.8900146484375]\n", + "epsilon:0.0009833015279105794 step:4435 episode:222 last_score -38.87445205688477 Profit 0.0 Loss [2502.172607421875]\n", + "epsilon:0.0009833015279105794 step:4440 episode:222 last_score -38.87445205688477 Profit 0.0 Loss [822.802978515625]\n", + "epsilon:0.0009833015279105794 step:4445 episode:223 last_score -328.0068115234375 Profit 0.0 Loss [528.3248291015625]\n", + "epsilon:0.0009833015279105794 step:4450 episode:223 last_score -328.0068115234375 Profit 0.0 Loss [1861.6090087890625]\n", + "epsilon:0.0009833015279105794 step:4455 episode:223 last_score -328.0068115234375 Profit 0.0 Loss [805.793212890625]\n", + "epsilon:0.0009833015279105794 step:4460 episode:223 last_score -328.0068115234375 Profit 0.0 Loss [726.4046020507812]\n", + "epsilon:0.0009833015279105794 step:4465 episode:224 last_score -411.6746545410156 Profit 0.0 Loss [757.0769653320312]\n", + "epsilon:0.0009833015279105794 step:4470 episode:224 last_score -411.6746545410156 Profit 0.0 Loss [1086.65087890625]\n", + "epsilon:0.0009833015279105794 step:4475 episode:224 last_score -411.6746545410156 Profit 0.0 Loss [212.44320678710938]\n", + "epsilon:0.0009833015279105794 step:4480 episode:224 last_score -411.6746545410156 Profit -0.8238677978515625 Loss [654.9849243164062]\n", + "epsilon:0.0009833015279105794 step:4485 episode:225 last_score -34.069351806640626 Profit 12.309051513671875 Loss [1955.9156494140625]\n", + "epsilon:0.0009833015279105794 step:4490 episode:225 last_score -34.069351806640626 Profit 28.2294921875 Loss [986.17236328125]\n", + "epsilon:0.0009833015279105794 step:4495 episode:225 last_score -34.069351806640626 Profit 121.36514282226562 Loss [530.8795166015625]\n", + "epsilon:0.0009833015279105794 step:4500 episode:225 last_score -34.069351806640626 Profit 121.36514282226562 Loss [894.8396606445312]\n", + "epsilon:0.0009833015279105794 step:4505 episode:226 last_score 61.08746826171877 Profit 0.0 Loss [553.9195556640625]\n", + "epsilon:0.0009833015279105794 step:4510 episode:226 last_score 61.08746826171877 Profit 0.0 Loss [1385.6131591796875]\n", + "epsilon:0.0009833015279105794 step:4515 episode:226 last_score 61.08746826171877 Profit 355.582275390625 Loss [1091.0255126953125]\n", + "epsilon:0.0009833015279105794 step:4520 episode:226 last_score 61.08746826171877 Profit 355.582275390625 Loss [645.899658203125]\n", + "epsilon:0.0009833015279105794 step:4525 episode:227 last_score -179.1189379882813 Profit 0.0 Loss [1057.2296142578125]\n", + "epsilon:0.0009833015279105794 step:4530 episode:227 last_score -179.1189379882813 Profit 0.0 Loss [2892.4404296875]\n", + "epsilon:0.0009833015279105794 step:4535 episode:227 last_score -179.1189379882813 Profit 9.393157958984375 Loss [805.1488037109375]\n", + "epsilon:0.0009833015279105794 step:4540 episode:227 last_score -179.1189379882813 Profit 9.393157958984375 Loss [1046.2645263671875]\n", + "epsilon:0.0009833015279105794 step:4545 episode:228 last_score -17.83287979125977 Profit 0.0 Loss [950.2728271484375]\n", + "epsilon:0.0009833015279105794 step:4550 episode:228 last_score -17.83287979125977 Profit 33.50132751464844 Loss [910.3682250976562]\n", + "epsilon:0.0009833015279105794 step:4555 episode:228 last_score -17.83287979125977 Profit 45.316375732421875 Loss [1312.71240234375]\n", + "epsilon:0.0009833015279105794 step:4560 episode:228 last_score -17.83287979125977 Profit 45.316375732421875 Loss [1042.0057373046875]\n", + "epsilon:0.0009833015279105794 step:4565 episode:229 last_score 20.485502777099608 Profit 0.0 Loss [2454.130615234375]\n", + "epsilon:0.0009833015279105794 step:4570 episode:229 last_score 20.485502777099608 Profit -8.92303466796875 Loss [1543.3409423828125]\n", + "epsilon:0.0009833015279105794 step:4575 episode:229 last_score 20.485502777099608 Profit -6.7964630126953125 Loss [509.372314453125]\n", + "epsilon:0.0009833015279105794 step:4580 episode:229 last_score 20.485502777099608 Profit -6.7964630126953125 Loss [360.2431945800781]\n", + "epsilon:0.0009833015279105794 step:4585 episode:230 last_score -39.490228424072264 Profit 0.0 Loss [1517.459716796875]\n", + "epsilon:0.0009833015279105794 step:4590 episode:230 last_score -39.490228424072264 Profit 9.062171936035156 Loss [348.1840515136719]\n", + "epsilon:0.0009833015279105794 step:4595 episode:230 last_score -39.490228424072264 Profit 9.062171936035156 Loss [1426.1680908203125]\n", + "epsilon:0.0009833015279105794 step:4600 episode:230 last_score -39.490228424072264 Profit 9.062171936035156 Loss [2233.1748046875]\n", + "epsilon:0.0009833015279105794 step:4605 episode:231 last_score -12.926935348510746 Profit 0.0 Loss [2222.59912109375]\n", + "epsilon:0.0009833015279105794 step:4610 episode:231 last_score -12.926935348510746 Profit 0.0 Loss [722.927490234375]\n", + "epsilon:0.0009833015279105794 step:4615 episode:231 last_score -12.926935348510746 Profit 0.0 Loss [913.4012451171875]\n", + "epsilon:0.0009833015279105794 step:4620 episode:231 last_score -12.926935348510746 Profit 0.0 Loss [769.0770874023438]\n", + "epsilon:0.0009833015279105794 step:4625 episode:232 last_score -19.865259323120114 Profit 0.0 Loss [250.60142517089844]\n", + "epsilon:0.0009833015279105794 step:4630 episode:232 last_score -19.865259323120114 Profit 0.0 Loss [1407.14453125]\n", + "epsilon:0.0009833015279105794 step:4635 episode:232 last_score -19.865259323120114 Profit 9.47698974609375 Loss [794.9351806640625]\n", + "epsilon:0.0009833015279105794 step:4640 episode:232 last_score -19.865259323120114 Profit 9.47698974609375 Loss [2628.520263671875]\n", + "epsilon:0.0009833015279105794 step:4645 episode:233 last_score -66.66860931396485 Profit 0.0 Loss [773.81787109375]\n", + "epsilon:0.0009833015279105794 step:4650 episode:233 last_score -66.66860931396485 Profit 0.0 Loss [694.932373046875]\n", + "epsilon:0.0009833015279105794 step:4655 episode:233 last_score -66.66860931396485 Profit -16.590972900390625 Loss [1134.97216796875]\n", + "epsilon:0.0009833015279105794 step:4660 episode:233 last_score -66.66860931396485 Profit -11.2685546875 Loss [243.07415771484375]\n", + "epsilon:0.0009833015279105794 step:4665 episode:234 last_score -71.53654663085938 Profit 0.0 Loss [466.1736755371094]\n", + "epsilon:0.0009833015279105794 step:4670 episode:234 last_score -71.53654663085938 Profit 25.730850219726562 Loss [1157.78466796875]\n", + "epsilon:0.0009833015279105794 step:4675 episode:234 last_score -71.53654663085938 Profit 42.2615966796875 Loss [696.3045043945312]\n", + "epsilon:0.0009833015279105794 step:4680 episode:234 last_score -71.53654663085938 Profit 55.64476013183594 Loss [713.8610229492188]\n", + "epsilon:0.0009833015279105794 step:4685 episode:235 last_score 26.413237152099608 Profit 19.081207275390625 Loss [498.94696044921875]\n", + "epsilon:0.0009833015279105794 step:4690 episode:235 last_score 26.413237152099608 Profit 19.081207275390625 Loss [399.1319580078125]\n", + "epsilon:0.0009833015279105794 step:4695 episode:235 last_score 26.413237152099608 Profit 40.148040771484375 Loss [807.24560546875]\n", + "epsilon:0.0009833015279105794 step:4700 episode:235 last_score 26.413237152099608 Profit 76.47024536132812 Loss [1473.5787353515625]\n", + "epsilon:0.0009833015279105794 step:4705 episode:236 last_score 47.29473571777344 Profit 6.708251953125 Loss [3161.922607421875]\n", + "epsilon:0.0009833015279105794 step:4710 episode:236 last_score 47.29473571777344 Profit 10.753280639648438 Loss [1458.0565185546875]\n", + "epsilon:0.0009833015279105794 step:4715 episode:236 last_score 47.29473571777344 Profit 10.753280639648438 Loss [316.0935974121094]\n", + "epsilon:0.0009833015279105794 step:4720 episode:236 last_score 47.29473571777344 Profit 10.753280639648438 Loss [1049.1661376953125]\n", + "epsilon:0.0009833015279105794 step:4725 episode:237 last_score -4.927978515625002 Profit 0.0 Loss [845.0460205078125]\n", + "epsilon:0.0009833015279105794 step:4730 episode:237 last_score -4.927978515625002 Profit 0.0 Loss [784.1881103515625]\n", + "epsilon:0.0009833015279105794 step:4735 episode:237 last_score -4.927978515625002 Profit 0.0 Loss [495.7832336425781]\n", + "epsilon:0.0009833015279105794 step:4740 episode:237 last_score -4.927978515625002 Profit -839.0269775390625 Loss [452.4847717285156]\n", + "epsilon:0.0009833015279105794 step:4745 episode:238 last_score -1258.2616357421875 Profit 10.877731323242188 Loss [1233.5567626953125]\n", + "epsilon:0.0009833015279105794 step:4750 episode:238 last_score -1258.2616357421875 Profit 3.0631561279296875 Loss [1480.477783203125]\n", + "epsilon:0.0009833015279105794 step:4755 episode:238 last_score -1258.2616357421875 Profit 3.0631561279296875 Loss [2155.053955078125]\n", + "epsilon:0.0009833015279105794 step:4760 episode:238 last_score -1258.2616357421875 Profit -14.00927734375 Loss [777.5703125]\n", + "epsilon:0.0009833015279105794 step:4765 episode:239 last_score -39.5157601928711 Profit 0.0 Loss [1426.177001953125]\n", + "epsilon:0.0009833015279105794 step:4770 episode:239 last_score -39.5157601928711 Profit 0.0 Loss [1035.77978515625]\n", + "epsilon:0.0009833015279105794 step:4775 episode:239 last_score -39.5157601928711 Profit 26.725814819335938 Loss [1544.40576171875]\n", + "epsilon:0.0009833015279105794 step:4780 episode:239 last_score -39.5157601928711 Profit 43.76206970214844 Loss [1443.962646484375]\n", + "epsilon:0.0009833015279105794 step:4785 episode:240 last_score -21.544026184082025 Profit 0.0 Loss [690.450439453125]\n", + "epsilon:0.0009833015279105794 step:4790 episode:240 last_score -21.544026184082025 Profit 0.0 Loss [1659.7242431640625]\n", + "epsilon:0.0009833015279105794 step:4795 episode:240 last_score -21.544026184082025 Profit 0.0 Loss [306.7471618652344]\n", + "epsilon:0.0009833015279105794 step:4800 episode:240 last_score -21.544026184082025 Profit -9.128997802734375 Loss [1132.07861328125]\n", + "epsilon:0.0009833015279105794 step:4805 episode:241 last_score -9.732988357543949 Profit 0.0 Loss [285.4210510253906]\n", + "epsilon:0.0009833015279105794 step:4810 episode:241 last_score -9.732988357543949 Profit 0.0 Loss [785.0532836914062]\n", + "epsilon:0.0009833015279105794 step:4815 episode:241 last_score -9.732988357543949 Profit -7.572662353515625 Loss [673.0296020507812]\n", + "epsilon:0.0009833015279105794 step:4820 episode:241 last_score -9.732988357543949 Profit -7.572662353515625 Loss [1023.0925903320312]\n", + "epsilon:0.0009833015279105794 step:4825 episode:242 last_score -178.77785766601562 Profit 370.45458984375 Loss [855.7435913085938]\n", + "epsilon:0.0009833015279105794 step:4830 episode:242 last_score -178.77785766601562 Profit 370.45458984375 Loss [709.695068359375]\n", + "epsilon:0.0009833015279105794 step:4835 episode:242 last_score -178.77785766601562 Profit 370.45458984375 Loss [857.8800048828125]\n", + "epsilon:0.0009833015279105794 step:4840 episode:242 last_score -178.77785766601562 Profit 986.112548828125 Loss [962.1507568359375]\n", + "epsilon:0.0009833015279105794 step:4845 episode:243 last_score 1252.2026293945312 Profit 0.0 Loss [640.199462890625]\n", + "epsilon:0.0009833015279105794 step:4850 episode:243 last_score 1252.2026293945312 Profit 0.0 Loss [874.3414306640625]\n", + "epsilon:0.0009833015279105794 step:4855 episode:243 last_score 1252.2026293945312 Profit 0.0 Loss [1672.9876708984375]\n", + "epsilon:0.0009833015279105794 step:4860 episode:243 last_score 1252.2026293945312 Profit 0.0 Loss [397.2183837890625]\n", + "epsilon:0.0009833015279105794 step:4865 episode:244 last_score -92.65495635986329 Profit 0.0 Loss [563.3331909179688]\n", + "epsilon:0.0009833015279105794 step:4870 episode:244 last_score -92.65495635986329 Profit 0.0 Loss [820.837646484375]\n", + "epsilon:0.0009833015279105794 step:4875 episode:244 last_score -92.65495635986329 Profit 0.0 Loss [460.6107177734375]\n", + "epsilon:0.0009833015279105794 step:4880 episode:244 last_score -92.65495635986329 Profit 0.0 Loss [1026.6156005859375]\n", + "epsilon:0.0009833015279105794 step:4885 episode:245 last_score -106.82715057373046 Profit 0.0 Loss [561.4176025390625]\n", + "epsilon:0.0009833015279105794 step:4890 episode:245 last_score -106.82715057373046 Profit 0.0 Loss [1239.72509765625]\n", + "epsilon:0.0009833015279105794 step:4895 episode:245 last_score -106.82715057373046 Profit 0.0 Loss [650.2647705078125]\n", + "epsilon:0.0009833015279105794 step:4900 episode:245 last_score -106.82715057373046 Profit -2.790618896484375 Loss [767.273681640625]\n", + "epsilon:0.0009833015279105794 step:4905 episode:246 last_score -50.663924865722656 Profit 0.0 Loss [2974.60302734375]\n", + "epsilon:0.0009833015279105794 step:4910 episode:246 last_score -50.663924865722656 Profit 0.0 Loss [508.26837158203125]\n", + "epsilon:0.0009833015279105794 step:4915 episode:246 last_score -50.663924865722656 Profit 73.603515625 Loss [1097.1402587890625]\n", + "epsilon:0.0009833015279105794 step:4920 episode:246 last_score -50.663924865722656 Profit 144.071533203125 Loss [501.06793212890625]\n", + "epsilon:0.0009833015279105794 step:4925 episode:247 last_score -385.136767578125 Profit 0.0 Loss [639.7947387695312]\n", + "epsilon:0.0009833015279105794 step:4930 episode:247 last_score -385.136767578125 Profit 0.0 Loss [542.8018188476562]\n", + "epsilon:0.0009833015279105794 step:4935 episode:247 last_score -385.136767578125 Profit 0.0 Loss [683.8798217773438]\n", + "epsilon:0.0009833015279105794 step:4940 episode:247 last_score -385.136767578125 Profit 0.0 Loss [2842.11572265625]\n", + "epsilon:0.0009833015279105794 step:4945 episode:248 last_score -253.7510986328125 Profit 0.0 Loss [950.5928344726562]\n", + "epsilon:0.0009833015279105794 step:4950 episode:248 last_score -253.7510986328125 Profit 0.0 Loss [1272.6251220703125]\n", + "epsilon:0.0009833015279105794 step:4955 episode:248 last_score -253.7510986328125 Profit 0.0 Loss [978.46826171875]\n", + "epsilon:0.0009833015279105794 step:4960 episode:248 last_score -253.7510986328125 Profit 0.0 Loss [823.8372802734375]\n", + "epsilon:0.0009833015279105794 step:4965 episode:249 last_score -158.67054748535156 Profit 0.0 Loss [1748.671875]\n", + "epsilon:0.0009833015279105794 step:4970 episode:249 last_score -158.67054748535156 Profit -33.0869140625 Loss [452.84735107421875]\n", + "epsilon:0.0009833015279105794 step:4975 episode:249 last_score -158.67054748535156 Profit -33.0869140625 Loss [2947.355224609375]\n", + "epsilon:0.0009833015279105794 step:4980 episode:249 last_score -158.67054748535156 Profit -33.0869140625 Loss [526.799072265625]\n", + "epsilon:0.0009833015279105794 step:4985 episode:250 last_score -97.53999755859375 Profit 0.0 Loss [1825.1065673828125]\n", + "epsilon:0.0009833015279105794 step:4990 episode:250 last_score -97.53999755859375 Profit 0.0 Loss [2264.25]\n", + "epsilon:0.0009833015279105794 step:4995 episode:250 last_score -97.53999755859375 Profit 0.0 Loss [1841.4532470703125]\n", + "epsilon:0.0009833015279105794 step:5000 episode:250 last_score -97.53999755859375 Profit 0.0 Loss [1482.0078125]\n", + "epsilon:0.0009833015279105794 step:5005 episode:251 last_score -86.632080078125 Profit 0.0 Loss [518.497802734375]\n", + "epsilon:0.0009833015279105794 step:5010 episode:251 last_score -86.632080078125 Profit 0.0 Loss [644.2139892578125]\n", + "epsilon:0.0009833015279105794 step:5015 episode:251 last_score -86.632080078125 Profit 0.0 Loss [782.7613525390625]\n", + "epsilon:0.0009833015279105794 step:5020 episode:251 last_score -86.632080078125 Profit 0.0 Loss [806.8412475585938]\n", + "epsilon:0.0009833015279105794 step:5025 episode:252 last_score -357.98919677734375 Profit 0.0 Loss [830.9773559570312]\n", + "epsilon:0.0009833015279105794 step:5030 episode:252 last_score -357.98919677734375 Profit 0.0 Loss [910.8895263671875]\n", + "epsilon:0.0009833015279105794 step:5035 episode:252 last_score -357.98919677734375 Profit 0.0 Loss [440.35882568359375]\n", + "epsilon:0.0009833015279105794 step:5040 episode:252 last_score -357.98919677734375 Profit 0.0 Loss [709.4696655273438]\n", + "epsilon:0.0009833015279105794 step:5045 episode:253 last_score -171.4011898803711 Profit 0.0 Loss [2295.404296875]\n", + "epsilon:0.0009833015279105794 step:5050 episode:253 last_score -171.4011898803711 Profit 0.0 Loss [632.7366333007812]\n", + "epsilon:0.0009833015279105794 step:5055 episode:253 last_score -171.4011898803711 Profit 39.435516357421875 Loss [647.3543701171875]\n", + "epsilon:0.0009833015279105794 step:5060 episode:253 last_score -171.4011898803711 Profit 39.435516357421875 Loss [345.0923767089844]\n", + "epsilon:0.0009833015279105794 step:5065 episode:254 last_score -196.59353515625 Profit 0.0 Loss [1033.72802734375]\n", + "epsilon:0.0009833015279105794 step:5070 episode:254 last_score -196.59353515625 Profit 19.2918701171875 Loss [921.868896484375]\n", + "epsilon:0.0009833015279105794 step:5075 episode:254 last_score -196.59353515625 Profit 19.2918701171875 Loss [1480.1802978515625]\n", + "epsilon:0.0009833015279105794 step:5080 episode:254 last_score -196.59353515625 Profit 19.2918701171875 Loss [1242.1448974609375]\n", + "epsilon:0.0009833015279105794 step:5085 episode:255 last_score 24.559901580810546 Profit 0.0 Loss [593.8652954101562]\n", + "epsilon:0.0009833015279105794 step:5090 episode:255 last_score 24.559901580810546 Profit 0.0 Loss [1154.458740234375]\n", + "epsilon:0.0009833015279105794 step:5095 episode:255 last_score 24.559901580810546 Profit 0.0 Loss [760.3908081054688]\n", + "epsilon:0.0009833015279105794 step:5100 episode:255 last_score 24.559901580810546 Profit 0.0 Loss [1339.5411376953125]\n", + "epsilon:0.0009833015279105794 step:5105 episode:256 last_score -785.5903442382811 Profit 0.0 Loss [950.017333984375]\n", + "epsilon:0.0009833015279105794 step:5110 episode:256 last_score -785.5903442382811 Profit 0.0 Loss [1561.938720703125]\n", + "epsilon:0.0009833015279105794 step:5115 episode:256 last_score -785.5903442382811 Profit 0.0 Loss [773.2645263671875]\n", + "epsilon:0.0009833015279105794 step:5120 episode:256 last_score -785.5903442382811 Profit 0.0 Loss [838.7310791015625]\n", + "epsilon:0.0009833015279105794 step:5125 episode:257 last_score -25.323979339599607 Profit 7.012939453125 Loss [1070.0443115234375]\n", + "epsilon:0.0009833015279105794 step:5130 episode:257 last_score -25.323979339599607 Profit 7.012939453125 Loss [2005.9412841796875]\n", + "epsilon:0.0009833015279105794 step:5135 episode:257 last_score -25.323979339599607 Profit 7.012939453125 Loss [459.7632751464844]\n", + "epsilon:0.0009833015279105794 step:5140 episode:257 last_score -25.323979339599607 Profit 7.012939453125 Loss [1275.4063720703125]\n", + "epsilon:0.0009833015279105794 step:5145 episode:258 last_score -7.330002746582034 Profit 48.2349853515625 Loss [763.6040649414062]\n", + "epsilon:0.0009833015279105794 step:5150 episode:258 last_score -7.330002746582034 Profit 108.31097412109375 Loss [888.428466796875]\n", + "epsilon:0.0009833015279105794 step:5155 episode:258 last_score -7.330002746582034 Profit 112.70697021484375 Loss [1902.20556640625]\n", + "epsilon:0.0009833015279105794 step:5160 episode:258 last_score -7.330002746582034 Profit 184.48797607421875 Loss [1090.7064208984375]\n", + "epsilon:0.0009833015279105794 step:5165 episode:259 last_score 216.51551879882808 Profit 16.804161071777344 Loss [686.6370849609375]\n", + "epsilon:0.0009833015279105794 step:5170 episode:259 last_score 216.51551879882808 Profit 16.804161071777344 Loss [507.9825134277344]\n", + "epsilon:0.0009833015279105794 step:5175 episode:259 last_score 216.51551879882808 Profit 16.804161071777344 Loss [1970.657958984375]\n", + "epsilon:0.0009833015279105794 step:5180 episode:259 last_score 216.51551879882808 Profit 16.804161071777344 Loss [1159.2757568359375]\n", + "epsilon:0.0009833015279105794 step:5185 episode:260 last_score -19.025206146240233 Profit 0.0 Loss [872.9078979492188]\n", + "epsilon:0.0009833015279105794 step:5190 episode:260 last_score -19.025206146240233 Profit -3.3604736328125 Loss [1086.6600341796875]\n", + "epsilon:0.0009833015279105794 step:5195 episode:260 last_score -19.025206146240233 Profit -3.3604736328125 Loss [3572.677490234375]\n", + "epsilon:0.0009833015279105794 step:5200 episode:260 last_score -19.025206146240233 Profit -3.3604736328125 Loss [778.3804931640625]\n", + "epsilon:0.0009833015279105794 step:5205 episode:261 last_score -556.8948815917968 Profit 0.0 Loss [792.3167114257812]\n", + "epsilon:0.0009833015279105794 step:5210 episode:261 last_score -556.8948815917968 Profit 0.0 Loss [564.5901489257812]\n", + "epsilon:0.0009833015279105794 step:5215 episode:261 last_score -556.8948815917968 Profit -21.9439697265625 Loss [547.922119140625]\n", + "epsilon:0.0009833015279105794 step:5220 episode:261 last_score -556.8948815917968 Profit -21.9439697265625 Loss [1886.6199951171875]\n", + "epsilon:0.0009833015279105794 step:5225 episode:262 last_score -140.07094543457032 Profit 0.0 Loss [2233.560302734375]\n", + "epsilon:0.0009833015279105794 step:5230 episode:262 last_score -140.07094543457032 Profit 0.0 Loss [594.6702270507812]\n", + "epsilon:0.0009833015279105794 step:5235 episode:262 last_score -140.07094543457032 Profit 0.0 Loss [1550.9407958984375]\n", + "epsilon:0.0009833015279105794 step:5240 episode:262 last_score -140.07094543457032 Profit 0.0 Loss [984.3479614257812]\n", + "epsilon:0.0009833015279105794 step:5245 episode:263 last_score -80.91436645507812 Profit 0.0 Loss [2835.909912109375]\n", + "epsilon:0.0009833015279105794 step:5250 episode:263 last_score -80.91436645507812 Profit 1.44940185546875 Loss [1356.2471923828125]\n", + "epsilon:0.0009833015279105794 step:5255 episode:263 last_score -80.91436645507812 Profit 10.005813598632812 Loss [1294.7091064453125]\n", + "epsilon:0.0009833015279105794 step:5260 episode:263 last_score -80.91436645507812 Profit 10.005813598632812 Loss [944.7119750976562]\n", + "epsilon:0.0009833015279105794 step:5265 episode:264 last_score -6.462390747070313 Profit 0.0 Loss [1018.9400024414062]\n", + "epsilon:0.0009833015279105794 step:5270 episode:264 last_score -6.462390747070313 Profit 0.0 Loss [519.6035766601562]\n", + "epsilon:0.0009833015279105794 step:5275 episode:264 last_score -6.462390747070313 Profit 24.45581817626953 Loss [772.61767578125]\n", + "epsilon:0.0009833015279105794 step:5280 episode:264 last_score -6.462390747070313 Profit 24.45581817626953 Loss [397.1816711425781]\n", + "epsilon:0.0009833015279105794 step:5285 episode:265 last_score 1.6511288452148434 Profit 17.9764404296875 Loss [1569.4642333984375]\n", + "epsilon:0.0009833015279105794 step:5290 episode:265 last_score 1.6511288452148434 Profit 1.5624847412109375 Loss [476.02227783203125]\n", + "epsilon:0.0009833015279105794 step:5295 episode:265 last_score 1.6511288452148434 Profit 6.965248107910156 Loss [876.5223388671875]\n", + "epsilon:0.0009833015279105794 step:5300 episode:265 last_score 1.6511288452148434 Profit 16.152015686035156 Loss [2265.810546875]\n", + "epsilon:0.0009833015279105794 step:5305 episode:266 last_score 18.83384811401368 Profit 0.0 Loss [871.6963500976562]\n", + "epsilon:0.0009833015279105794 step:5310 episode:266 last_score 18.83384811401368 Profit 0.0 Loss [2007.2403564453125]\n", + "epsilon:0.0009833015279105794 step:5315 episode:266 last_score 18.83384811401368 Profit 0.0 Loss [847.6343994140625]\n", + "epsilon:0.0009833015279105794 step:5320 episode:266 last_score 18.83384811401368 Profit 0.0 Loss [947.0127563476562]\n", + "epsilon:0.0009833015279105794 step:5325 episode:267 last_score -594.9999609375001 Profit 33.45501708984375 Loss [557.9074096679688]\n", + "epsilon:0.0009833015279105794 step:5330 episode:267 last_score -594.9999609375001 Profit 34.969970703125 Loss [825.1599731445312]\n", + "epsilon:0.0009833015279105794 step:5335 episode:267 last_score -594.9999609375001 Profit 34.969970703125 Loss [997.1265869140625]\n", + "epsilon:0.0009833015279105794 step:5340 episode:267 last_score -594.9999609375001 Profit -91.15399169921875 Loss [3268.75927734375]\n", + "epsilon:0.0009833015279105794 step:5345 episode:268 last_score -249.07345947265628 Profit 0.394989013671875 Loss [2957.016357421875]\n", + "epsilon:0.0009833015279105794 step:5350 episode:268 last_score -249.07345947265628 Profit 0.394989013671875 Loss [1512.5096435546875]\n", + "epsilon:0.0009833015279105794 step:5355 episode:268 last_score -249.07345947265628 Profit -5.0250091552734375 Loss [219.24679565429688]\n", + "epsilon:0.0009833015279105794 step:5360 episode:268 last_score -249.07345947265628 Profit 5.4210052490234375 Loss [1057.6466064453125]\n", + "epsilon:0.0009833015279105794 step:5365 episode:269 last_score -8.041907806396482 Profit 0.0 Loss [887.988525390625]\n", + "epsilon:0.0009833015279105794 step:5370 episode:269 last_score -8.041907806396482 Profit 213.558349609375 Loss [1030.024658203125]\n", + "epsilon:0.0009833015279105794 step:5375 episode:269 last_score -8.041907806396482 Profit 309.5550537109375 Loss [2583.83056640625]\n", + "epsilon:0.0009833015279105794 step:5380 episode:269 last_score -8.041907806396482 Profit 309.5550537109375 Loss [270.1651916503906]\n", + "epsilon:0.0009833015279105794 step:5385 episode:270 last_score 96.00610229492185 Profit 0.0 Loss [584.6072998046875]\n", + "epsilon:0.0009833015279105794 step:5390 episode:270 last_score 96.00610229492185 Profit 0.83447265625 Loss [1705.938720703125]\n", + "epsilon:0.0009833015279105794 step:5395 episode:270 last_score 96.00610229492185 Profit 0.83447265625 Loss [1642.7796630859375]\n", + "epsilon:0.0009833015279105794 step:5400 episode:270 last_score 96.00610229492185 Profit 226.908935546875 Loss [2188.154052734375]\n", + "epsilon:0.0009833015279105794 step:5405 episode:271 last_score -75.10574951171868 Profit 0.0 Loss [865.5610961914062]\n", + "epsilon:0.0009833015279105794 step:5410 episode:271 last_score -75.10574951171868 Profit 93.498046875 Loss [306.5556335449219]\n", + "epsilon:0.0009833015279105794 step:5415 episode:271 last_score -75.10574951171868 Profit 282.66259765625 Loss [478.8494567871094]\n", + "epsilon:0.0009833015279105794 step:5420 episode:271 last_score -75.10574951171868 Profit 282.66259765625 Loss [1234.5439453125]\n", + "epsilon:0.0009833015279105794 step:5425 episode:272 last_score -316.954384765625 Profit 257.16796875 Loss [832.07421875]\n", + "epsilon:0.0009833015279105794 step:5430 episode:272 last_score -316.954384765625 Profit 393.098388671875 Loss [1686.705810546875]\n", + "epsilon:0.0009833015279105794 step:5435 episode:272 last_score -316.954384765625 Profit 393.098388671875 Loss [439.2247619628906]\n", + "epsilon:0.0009833015279105794 step:5440 episode:272 last_score -316.954384765625 Profit 375.36767578125 Loss [1006.9620361328125]\n", + "epsilon:0.0009833015279105794 step:5445 episode:273 last_score 343.7551660156249 Profit 9.984695434570312 Loss [1387.3397216796875]\n", + "epsilon:0.0009833015279105794 step:5450 episode:273 last_score 343.7551660156249 Profit 14.02972412109375 Loss [1844.2607421875]\n", + "epsilon:0.0009833015279105794 step:5455 episode:273 last_score 343.7551660156249 Profit 14.02972412109375 Loss [1362.79296875]\n", + "epsilon:0.0009833015279105794 step:5460 episode:273 last_score 343.7551660156249 Profit 14.02972412109375 Loss [260.2430725097656]\n", + "epsilon:0.0009833015279105794 step:5465 episode:274 last_score -18.98009963989258 Profit 0.0 Loss [368.0233459472656]\n", + "epsilon:0.0009833015279105794 step:5470 episode:274 last_score -18.98009963989258 Profit 0.0 Loss [1084.6656494140625]\n", + "epsilon:0.0009833015279105794 step:5475 episode:274 last_score -18.98009963989258 Profit -59.60504150390625 Loss [441.12628173828125]\n", + "epsilon:0.0009833015279105794 step:5480 episode:274 last_score -18.98009963989258 Profit 18.990966796875 Loss [2549.681640625]\n", + "epsilon:0.0009833015279105794 step:5485 episode:275 last_score -144.01936370849612 Profit 0.0 Loss [1213.5706787109375]\n", + "epsilon:0.0009833015279105794 step:5490 episode:275 last_score -144.01936370849612 Profit 0.0 Loss [348.6705322265625]\n", + "epsilon:0.0009833015279105794 step:5495 episode:275 last_score -144.01936370849612 Profit 0.0 Loss [657.8125610351562]\n", + "epsilon:0.0009833015279105794 step:5500 episode:275 last_score -144.01936370849612 Profit 0.0 Loss [629.4419555664062]\n", + "epsilon:0.0009833015279105794 step:5505 episode:276 last_score -554.0372973632813 Profit 0.0 Loss [220.81764221191406]\n", + "epsilon:0.0009833015279105794 step:5510 episode:276 last_score -554.0372973632813 Profit 0.0 Loss [266.3315734863281]\n", + "epsilon:0.0009833015279105794 step:5515 episode:276 last_score -554.0372973632813 Profit 0.0 Loss [791.2078247070312]\n", + "epsilon:0.0009833015279105794 step:5520 episode:276 last_score -554.0372973632813 Profit 0.0 Loss [315.1714172363281]\n", + "epsilon:0.0009833015279105794 step:5525 episode:277 last_score -857.7310864257813 Profit 0.0 Loss [1416.64501953125]\n", + "epsilon:0.0009833015279105794 step:5530 episode:277 last_score -857.7310864257813 Profit 66.764404296875 Loss [1724.1192626953125]\n", + "epsilon:0.0009833015279105794 step:5535 episode:277 last_score -857.7310864257813 Profit 128.55615234375 Loss [734.7833862304688]\n", + "epsilon:0.0009833015279105794 step:5540 episode:277 last_score -857.7310864257813 Profit 264.520263671875 Loss [435.9913024902344]\n", + "epsilon:0.0009833015279105794 step:5545 episode:278 last_score -180.047060546875 Profit -2.354461669921875 Loss [195.29200744628906]\n", + "epsilon:0.0009833015279105794 step:5550 episode:278 last_score -180.047060546875 Profit -2.354461669921875 Loss [833.7620849609375]\n", + "epsilon:0.0009833015279105794 step:5555 episode:278 last_score -180.047060546875 Profit -2.354461669921875 Loss [426.955078125]\n", + "epsilon:0.0009833015279105794 step:5560 episode:278 last_score -180.047060546875 Profit -2.354461669921875 Loss [601.5980224609375]\n", + "epsilon:0.0009833015279105794 step:5565 episode:279 last_score -29.548711395263673 Profit 15.717010498046875 Loss [563.9603271484375]\n", + "epsilon:0.0009833015279105794 step:5570 episode:279 last_score -29.548711395263673 Profit 15.717010498046875 Loss [2170.01953125]\n", + "epsilon:0.0009833015279105794 step:5575 episode:279 last_score -29.548711395263673 Profit 15.717010498046875 Loss [291.9898376464844]\n", + "epsilon:0.0009833015279105794 step:5580 episode:279 last_score -29.548711395263673 Profit 15.717010498046875 Loss [616.0267333984375]\n", + "epsilon:0.0009833015279105794 step:5585 episode:280 last_score -130.2488702392578 Profit 184.0052490234375 Loss [773.5811767578125]\n", + "epsilon:0.0009833015279105794 step:5590 episode:280 last_score -130.2488702392578 Profit 184.0052490234375 Loss [1213.15625]\n", + "epsilon:0.0009833015279105794 step:5595 episode:280 last_score -130.2488702392578 Profit 402.81787109375 Loss [2303.964599609375]\n", + "epsilon:0.0009833015279105794 step:5600 episode:280 last_score -130.2488702392578 Profit 620.2230224609375 Loss [347.5394287109375]\n", + "epsilon:0.0009833015279105794 step:5605 episode:281 last_score 362.90034667968746 Profit 87.041015625 Loss [956.5386962890625]\n", + "epsilon:0.0009833015279105794 step:5610 episode:281 last_score 362.90034667968746 Profit 165.78857421875 Loss [1840.5665283203125]\n", + "epsilon:0.0009833015279105794 step:5615 episode:281 last_score 362.90034667968746 Profit 867.87255859375 Loss [1146.296142578125]\n", + "epsilon:0.0009833015279105794 step:5620 episode:281 last_score 362.90034667968746 Profit 1082.37939453125 Loss [992.43212890625]\n", + "epsilon:0.0009833015279105794 step:5625 episode:282 last_score 1072.083525390625 Profit 0.0 Loss [1730.134521484375]\n", + "epsilon:0.0009833015279105794 step:5630 episode:282 last_score 1072.083525390625 Profit 40.13800048828125 Loss [871.0663452148438]\n", + "epsilon:0.0009833015279105794 step:5635 episode:282 last_score 1072.083525390625 Profit 61.28399658203125 Loss [1044.5889892578125]\n", + "epsilon:0.0009833015279105794 step:5640 episode:282 last_score 1072.083525390625 Profit 61.28399658203125 Loss [3133.402099609375]\n", + "epsilon:0.0009833015279105794 step:5645 episode:283 last_score -7.957510986328118 Profit 0.0 Loss [1524.0723876953125]\n", + "epsilon:0.0009833015279105794 step:5650 episode:283 last_score -7.957510986328118 Profit 0.0 Loss [787.0302124023438]\n", + "epsilon:0.0009833015279105794 step:5655 episode:283 last_score -7.957510986328118 Profit 0.0 Loss [969.2706298828125]\n", + "epsilon:0.0009833015279105794 step:5660 episode:283 last_score -7.957510986328118 Profit 0.0 Loss [2336.04345703125]\n", + "epsilon:0.0009833015279105794 step:5665 episode:284 last_score -183.1675213623047 Profit 0.0 Loss [865.0423583984375]\n", + "epsilon:0.0009833015279105794 step:5670 episode:284 last_score -183.1675213623047 Profit 0.0 Loss [1090.283447265625]\n", + "epsilon:0.0009833015279105794 step:5675 episode:284 last_score -183.1675213623047 Profit -1.8477783203125 Loss [962.1195068359375]\n", + "epsilon:0.0009833015279105794 step:5680 episode:284 last_score -183.1675213623047 Profit 14.91192626953125 Loss [756.029052734375]\n", + "epsilon:0.0009833015279105794 step:5685 episode:285 last_score -24.25663482666016 Profit 0.0 Loss [801.0946655273438]\n", + "epsilon:0.0009833015279105794 step:5690 episode:285 last_score -24.25663482666016 Profit 0.0 Loss [713.1166381835938]\n", + "epsilon:0.0009833015279105794 step:5695 episode:285 last_score -24.25663482666016 Profit -195.1114501953125 Loss [873.6913452148438]\n", + "epsilon:0.0009833015279105794 step:5700 episode:285 last_score -24.25663482666016 Profit -195.1114501953125 Loss [755.2040405273438]\n", + "epsilon:0.0009833015279105794 step:5705 episode:286 last_score -737.699306640625 Profit -175.956298828125 Loss [385.9060974121094]\n", + "epsilon:0.0009833015279105794 step:5710 episode:286 last_score -737.699306640625 Profit -175.956298828125 Loss [916.4673461914062]\n", + "epsilon:0.0009833015279105794 step:5715 episode:286 last_score -737.699306640625 Profit -328.309814453125 Loss [1403.5308837890625]\n", + "epsilon:0.0009833015279105794 step:5720 episode:286 last_score -737.699306640625 Profit -21.187255859375 Loss [874.0543823242188]\n", + "epsilon:0.0009833015279105794 step:5725 episode:287 last_score -916.753935546875 Profit 49.93931579589844 Loss [641.3817749023438]\n", + "epsilon:0.0009833015279105794 step:5730 episode:287 last_score -916.753935546875 Profit 49.93931579589844 Loss [933.1570434570312]\n", + "epsilon:0.0009833015279105794 step:5735 episode:287 last_score -916.753935546875 Profit 56.38703918457031 Loss [473.8637390136719]\n", + "epsilon:0.0009833015279105794 step:5740 episode:287 last_score -916.753935546875 Profit 76.14532470703125 Loss [469.90118408203125]\n", + "epsilon:0.0009833015279105794 step:5745 episode:288 last_score 58.80071517944336 Profit 125.8653564453125 Loss [1144.3734130859375]\n", + "epsilon:0.0009833015279105794 step:5750 episode:288 last_score 58.80071517944336 Profit 125.8653564453125 Loss [968.767822265625]\n", + "epsilon:0.0009833015279105794 step:5755 episode:288 last_score 58.80071517944336 Profit 125.8653564453125 Loss [1812.4940185546875]\n", + "epsilon:0.0009833015279105794 step:5760 episode:288 last_score 58.80071517944336 Profit -123.7147216796875 Loss [1873.36767578125]\n", + "epsilon:0.0009833015279105794 step:5765 episode:289 last_score -364.63886962890626 Profit 6.683807373046875 Loss [2518.5380859375]\n", + "epsilon:0.0009833015279105794 step:5770 episode:289 last_score -364.63886962890626 Profit 19.695281982421875 Loss [280.10235595703125]\n", + "epsilon:0.0009833015279105794 step:5775 episode:289 last_score -364.63886962890626 Profit 19.695281982421875 Loss [430.1905822753906]\n", + "epsilon:0.0009833015279105794 step:5780 episode:289 last_score -364.63886962890626 Profit 19.695281982421875 Loss [326.0204162597656]\n", + "epsilon:0.0009833015279105794 step:5785 episode:290 last_score -31.103904418945312 Profit 0.0 Loss [758.3153076171875]\n", + "epsilon:0.0009833015279105794 step:5790 episode:290 last_score -31.103904418945312 Profit 7.3195343017578125 Loss [1052.4534912109375]\n", + "epsilon:0.0009833015279105794 step:5795 episode:290 last_score -31.103904418945312 Profit 7.3195343017578125 Loss [1555.006591796875]\n", + "epsilon:0.0009833015279105794 step:5800 episode:290 last_score -31.103904418945312 Profit 3.6779327392578125 Loss [978.0491943359375]\n", + "epsilon:0.0009833015279105794 step:5805 episode:291 last_score -8.82629379272461 Profit 0.0 Loss [377.4199523925781]\n", + "epsilon:0.0009833015279105794 step:5810 episode:291 last_score -8.82629379272461 Profit 0.0 Loss [919.2157592773438]\n", + "epsilon:0.0009833015279105794 step:5815 episode:291 last_score -8.82629379272461 Profit -16.590972900390625 Loss [1009.5038452148438]\n", + "epsilon:0.0009833015279105794 step:5820 episode:291 last_score -8.82629379272461 Profit -6.8231201171875 Loss [837.3013305664062]\n", + "epsilon:0.0009833015279105794 step:5825 episode:292 last_score -63.06319976806641 Profit 0.0 Loss [1541.2894287109375]\n", + "epsilon:0.0009833015279105794 step:5830 episode:292 last_score -63.06319976806641 Profit 0.0 Loss [1495.6021728515625]\n", + "epsilon:0.0009833015279105794 step:5835 episode:292 last_score -63.06319976806641 Profit 0.0 Loss [1247.7227783203125]\n", + "epsilon:0.0009833015279105794 step:5840 episode:292 last_score -63.06319976806641 Profit 0.0 Loss [2496.55224609375]\n", + "epsilon:0.0009833015279105794 step:5845 episode:293 last_score -35.436476135253905 Profit 8.598403930664062 Loss [730.999267578125]\n", + "epsilon:0.0009833015279105794 step:5850 episode:293 last_score -35.436476135253905 Profit 8.598403930664062 Loss [313.3891906738281]\n", + "epsilon:0.0009833015279105794 step:5855 episode:293 last_score -35.436476135253905 Profit 31.273849487304688 Loss [611.3030395507812]\n", + "epsilon:0.0009833015279105794 step:5860 episode:293 last_score -35.436476135253905 Profit 37.75 Loss [594.8771362304688]\n", + "epsilon:0.0009833015279105794 step:5865 episode:294 last_score 35.91881561279297 Profit 0.0 Loss [789.1023559570312]\n", + "epsilon:0.0009833015279105794 step:5870 episode:294 last_score 35.91881561279297 Profit 0.0 Loss [656.374755859375]\n", + "epsilon:0.0009833015279105794 step:5875 episode:294 last_score 35.91881561279297 Profit -3.91522216796875 Loss [2631.41748046875]\n", + "epsilon:0.0009833015279105794 step:5880 episode:294 last_score 35.91881561279297 Profit -3.91522216796875 Loss [1282.4339599609375]\n", + "epsilon:0.0009833015279105794 step:5885 episode:295 last_score -83.20057373046875 Profit 203.75830078125 Loss [1179.8226318359375]\n", + "epsilon:0.0009833015279105794 step:5890 episode:295 last_score -83.20057373046875 Profit 203.75830078125 Loss [788.7412719726562]\n", + "epsilon:0.0009833015279105794 step:5895 episode:295 last_score -83.20057373046875 Profit 203.75830078125 Loss [892.6257934570312]\n", + "epsilon:0.0009833015279105794 step:5900 episode:295 last_score -83.20057373046875 Profit 89.2962646484375 Loss [813.0120239257812]\n", + "epsilon:0.0009833015279105794 step:5905 episode:296 last_score -183.2893859863281 Profit 10.177001953125 Loss [903.1181030273438]\n", + "epsilon:0.0009833015279105794 step:5910 episode:296 last_score -183.2893859863281 Profit 224.3525390625 Loss [730.5260009765625]\n", + "epsilon:0.0009833015279105794 step:5915 episode:296 last_score -183.2893859863281 Profit 224.3525390625 Loss [470.5635681152344]\n", + "epsilon:0.0009833015279105794 step:5920 episode:296 last_score -183.2893859863281 Profit -179.682861328125 Loss [399.6322021484375]\n", + "epsilon:0.0009833015279105794 step:5925 episode:297 last_score -956.6921997070312 Profit 0.0 Loss [687.5648193359375]\n", + "epsilon:0.0009833015279105794 step:5930 episode:297 last_score -956.6921997070312 Profit -36.97314453125 Loss [1358.3575439453125]\n", + "epsilon:0.0009833015279105794 step:5935 episode:297 last_score -956.6921997070312 Profit 97.90087890625 Loss [898.564208984375]\n", + "epsilon:0.0009833015279105794 step:5940 episode:297 last_score -956.6921997070312 Profit 97.90087890625 Loss [969.327392578125]\n", + "epsilon:0.0009833015279105794 step:5945 episode:298 last_score -447.53942626953125 Profit 3.7310943603515625 Loss [2462.7783203125]\n", + "epsilon:0.0009833015279105794 step:5950 episode:298 last_score -447.53942626953125 Profit 3.7310943603515625 Loss [325.6250305175781]\n", + "epsilon:0.0009833015279105794 step:5955 episode:298 last_score -447.53942626953125 Profit 3.7310943603515625 Loss [1820.7918701171875]\n", + "epsilon:0.0009833015279105794 step:5960 episode:298 last_score -447.53942626953125 Profit 3.7310943603515625 Loss [655.8548583984375]\n", + "epsilon:0.0009833015279105794 step:5965 episode:299 last_score -30.049903259277347 Profit 0.0 Loss [1538.5369873046875]\n", + "epsilon:0.0009833015279105794 step:5970 episode:299 last_score -30.049903259277347 Profit -0.625030517578125 Loss [360.44451904296875]\n", + "epsilon:0.0009833015279105794 step:5975 episode:299 last_score -30.049903259277347 Profit 1.4778900146484375 Loss [1337.63525390625]\n", + "epsilon:0.0009833015279105794 step:5980 episode:299 last_score -30.049903259277347 Profit -5.6605072021484375 Loss [637.25439453125]\n", + "epsilon:0.0009833015279105794 step:5985 episode:300 last_score -32.26794372558594 Profit 0.0 Loss [787.7514038085938]\n", + "epsilon:0.0009833015279105794 step:5990 episode:300 last_score -32.26794372558594 Profit 0.0 Loss [2046.79150390625]\n", + "epsilon:0.0009833015279105794 step:5995 episode:300 last_score -32.26794372558594 Profit 0.0 Loss [1339.264404296875]\n", + "epsilon:0.0009833015279105794 step:6000 episode:300 last_score -32.26794372558594 Profit 0.0 Loss [1237.489501953125]\n" + ] + } + ], + "source": [ + "# create env\n", + "max_steps = 20 \n", + "env = CustTradingEnv(df=eth_train, max_steps=max_steps)\n", + "\n", + "model = DQN(env=env, replay_buffer_size=10_000)\n", + "model.learn(total_steps=6_000)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "INFO:tensorflow:Assets written to: ./alt/fin_rl_dqn_v1/assets\n" + ] + }, + { + "data": { + "text/plain": [ + "['./alt/fin_rl_dqn_v1.h5_scaler']" + ] + }, + "execution_count": 70, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model.save(\"./alt/fin_rl_dqn_v1\")\n", + "joblib.dump(env.get_scaler(),\"./alt/fin_rl_dqn_v1.h5_scaler\")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "\n", + "def evaluate_agent(env, max_steps, n_eval_episodes, model, random=False):\n", + " \"\"\"\n", + " Evaluate the agent for ``n_eval_episodes`` episodes and returns average reward and std of reward.\n", + " :param env: The evaluation environment\n", + " :param n_eval_episodes: Number of episode to evaluate the agent\n", + " :param model: The DQN model\n", + " \"\"\"\n", + " episode_rewards = []\n", + " episode_profits = []\n", + " for episode in tqdm(range(n_eval_episodes), disable=random):\n", + " state = env.reset()\n", + " step = 0\n", + " done = False\n", + " total_rewards_ep = 0\n", + " total_profit_ep = 0\n", + " \n", + " for step in range(max_steps):\n", + " # Take the action (index) that have the maximum expected future reward given that state\n", + " if random:\n", + " action = env.action_space.sample()\n", + " else:\n", + " action = model.play(state)\n", + " # print(action)\n", + " \n", + " new_state, reward, done, info = env.step(action)\n", + " total_rewards_ep += reward\n", + " \n", + " if done:\n", + " break\n", + " state = new_state\n", + "\n", + " episode_rewards.append(total_rewards_ep)\n", + " episode_profits.append(env.history['total_profit'][-1])\n", + " # print(env.history)\n", + " # env.render()\n", + " # assert 0\n", + "\n", + " mean_reward = np.mean(episode_rewards)\n", + " std_reward = np.std(episode_rewards)\n", + " mean_profit = np.mean(episode_profits)\n", + " std_profit = np.std(episode_profits)\n", + "\n", + " return mean_reward, std_reward, mean_profit, std_profit" + ] + }, + { + "cell_type": "code", + "execution_count": 87, + "metadata": {}, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "f0eff2ef3b0a4e12a23709db72722a25", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/1000 [00:00here for more info. View Jupyter log for further details." + ] + } + ], + "source": [ + "max_steps = 20 \n", + "env_test = CustTradingEnv(df=eth_test, max_steps=max_steps, random_start=True, scaler=env.get_scaler())\n", + "n_eval_episodes = 1000\n", + "\n", + "evaluate_agent(env_test, max_steps, n_eval_episodes, model)" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": {}, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "a7b0edb264fe43edbe5cea55fac21688", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/1 [00:00" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plt.figure(figsize=(15,6))\n", + "plt.cla()\n", + "env_l.render()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(-156.66986416870117,\n", + " 394.94783990529805,\n", + " 4.957175903320312,\n", + " 211.59187866264426)" + ] + }, + "execution_count": 84, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Test for random n_eval_episodes\n", + "max_steps = 20 \n", + "env_test_rand = CustTradingEnv(df=eth_test, max_steps=max_steps, random_start=True, scaler=env.get_scaler())\n", + "n_eval_episodes = 1000\n", + "\n", + "evaluate_agent(env_test_rand, max_steps, n_eval_episodes, model, random=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 85, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Mean profit 3.7792178955078124\n" + ] + } + ], + "source": [ + "# trade sequentially with random actions \n", + "max_steps = len(eth_test)\n", + "env_test = CustTradingEnv(df=eth_test, max_steps=max_steps, random_start=False, scaler=env.get_scaler())\n", + "n_eval_episodes = 1\n", + "\n", + "all_profit=[]\n", + "for i in range(1000):\n", + " _,_,profit,_=evaluate_agent(env_test, max_steps, n_eval_episodes, model, random=True)\n", + " all_profit.append(profit)\n", + "print(f\"Mean profit {np.mean(all_profit)}\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Results\n", + "\n", + "| Model | 1000 trades 20 steps | Sequential trading | 1000 trades 20 steps random actions | Sequential random|\n", + "|------------|----------------------|--------------------|-------------------------------------|------------------|\n", + "|Q-learning | 113.14 | 563.67 | -18.10 | 39.30 |\n", + "|DQN | 87.62 | 381.17 | 4.95 | 3.77 |\n", + "\n", + "\n", + "#### Actions are: Buy/Sell/Hold 1 ETH \n", + "1000 trades 20 steps - Made 1000 episodes, 20 trades each episode, result is the mean return of each episode \n", + "\n", + "Sequential trading (175 days)- Trade the test set sequentially from start to end day \n", + "\n", + "1000 trades 20 steps random actions - Made 1000 episodes, 20 trades each episode taking random actions \n", + "\n", + "Sequential random (175 days)- Trade the test set sequentially from start to end day with random actions " + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3.8.13 ('rl2')", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.13" + }, + "orig_nbformat": 4, + "vscode": { + "interpreter": { + "hash": "cd60ab8388a66026f336166410d6a8a46ddf65ece2e85ad2d46c8b98d87580d1" + } + }, + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "01a2dbcb714e40148b41c761fcf43147": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "20b0f38ec3234ff28a62a286cd57b933": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "PasswordModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "PasswordModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "PasswordView", + "continuous_update": true, + "description": "Token:", + "description_tooltip": null, + "disabled": false, + "layout": "IPY_MODEL_01a2dbcb714e40148b41c761fcf43147", + "placeholder": "​", + "style": "IPY_MODEL_90c874e91b304ee1a7ef147767ac00ce", + "value": "" + } + }, + "270cbb5d6e9c4b1e9e2f39c8b3b0c15f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "VBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "VBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "VBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_a02224a43d8d4af3bd31d326540d25da", + "IPY_MODEL_20b0f38ec3234ff28a62a286cd57b933", + "IPY_MODEL_f6c845330d6743c0b35c2c7ad834de77", + "IPY_MODEL_f1675c09d16a4251b403f9c56255f168", + "IPY_MODEL_c1a82965ae26479a98e4fdbde1e64ec2" + ], + "layout": "IPY_MODEL_3fa248114ac24656ba74923936a94d2d" + } + }, + "2dc5fa9aa3334dfcbdee9c238f2ef60b": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "3e753b0212644990b558c68853ff2041": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "3fa248114ac24656ba74923936a94d2d": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": "center", + "align_self": null, + "border": null, + "bottom": null, + "display": "flex", + "flex": null, + "flex_flow": "column", + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": "50%" + } + }, + "42d140b838b844819bc127afc1b7bc84": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "90c874e91b304ee1a7ef147767ac00ce": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "9d847f9a7d47458d8cd57d9b599e47c6": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "a02224a43d8d4af3bd31d326540d25da": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_caef095934ec47bbb8b64eab22049284", + "placeholder": "​", + "style": "IPY_MODEL_2dc5fa9aa3334dfcbdee9c238f2ef60b", + "value": "

Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file.
" + } + }, + "a2cfb91cf66447d7899292854bd64a07": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "c1a82965ae26479a98e4fdbde1e64ec2": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_9d847f9a7d47458d8cd57d9b599e47c6", + "placeholder": "​", + "style": "IPY_MODEL_42d140b838b844819bc127afc1b7bc84", + "value": "\nPro Tip: If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. " + } + }, + "caef095934ec47bbb8b64eab22049284": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "eaba3f1de4444aabadfea2a3dadb1d80": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "ee4a21bedc504171ad09d205d634b528": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ButtonStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ButtonStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "button_color": null, + "font_weight": "" + } + }, + "f1675c09d16a4251b403f9c56255f168": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ButtonModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ButtonModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ButtonView", + "button_style": "", + "description": "Login", + "disabled": false, + "icon": "", + "layout": "IPY_MODEL_a2cfb91cf66447d7899292854bd64a07", + "style": "IPY_MODEL_ee4a21bedc504171ad09d205d634b528", + "tooltip": "" + } + }, + "f6c845330d6743c0b35c2c7ad834de77": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "CheckboxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "CheckboxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "CheckboxView", + "description": "Add token as git credential?", + "description_tooltip": null, + "disabled": false, + "indent": true, + "layout": "IPY_MODEL_3e753b0212644990b558c68853ff2041", + "style": "IPY_MODEL_eaba3f1de4444aabadfea2a3dadb1d80", + "value": true + } + } + } + } + }, + "nbformat": 4, + "nbformat_minor": 0 +}