{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "nwaAZRu1NTiI" }, "source": [ "# DQN v2\n", "\n", "#### This version implements DQN with Keras\n", "#### Findings:\n", "Smaller NET then v1 does not work" ] }, { "cell_type": "code", "execution_count": 37, "metadata": { "id": "LNXxxKojNTiL" }, "outputs": [], "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", "\n", "import io\n", "import base64\n", "from IPython.display import HTML, Video\n" ] }, { "cell_type": "code", "execution_count": 57, "metadata": {}, "outputs": [], "source": [ "class DQN:\n", " def __init__(self, env=None, replay_buffer_size=1000, action_size=2):\n", " self.replay_buffer = deque(maxlen=replay_buffer_size)\n", "\n", " self.action_size = action_size\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 = 100\n", " self.learning_rate = 5e-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", " self.action_size = action_size\n", "\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(512, activation = 'relu'))\n", " model.add(layers.Dense(256, activation = 'relu'))\n", " model.add(layers.Dense(128, activation = 'relu'))\n", " model.add(layers.Dense(self.action_size, activation = 'linear'))\n", " # model.compile(optimizer = RMSprop(lr = self.lr, rho = 0.95, epsilon = 0.01), loss = \"mse\", metrics = ['accuracy'])\n", " \n", " optimizer = tf.keras.optimizers.Adam(learning_rate=self.learning_rate)\n", " # model.compile(loss='mse', optimizer=tf.keras.optimizers.RMSprop(lr = self.learning_rate, rho = 0.95, epsilon = 0.01), metrics = ['accuracy'])\n", " model.compile(loss='mse', optimizer=optimizer, metrics = ['accuracy'])\n", " return model\n", "\n", " def _min_max(self):\n", " \"\"\"Run some steps to get data to do MINMAX scale \"\"\"\n", " state_arr = []\n", " state_arr.append(self.env.observation_space.high)\n", " state_arr[0][1], state_arr[0][3] = 0,0\n", " state_arr.append(self.env.observation_space.low)\n", " state_arr[1][1], state_arr[1][3] = 0,0\n", " state = self.env.reset()\n", " for i in range(1000):\n", " random_action = self.env.action_space.sample()\n", " next_state, reward, done, info = self.env.step(random_action)\n", " state_arr.append(next_state)\n", " if done:\n", " state = self.env.reset()\n", "\n", " state_arr = np.array(state_arr)\n", " self.scaler = MinMaxScaler()\n", " self.scaler.fit(state_arr)\n", " # print(self.scaler.data_max_)\n", " # print(self.scaler.data_min_)\n", "\n", " def _get_scaled_state(self, state):\n", " return state\n", " # return self.scaler.transform(state.reshape(1,-1)).flatten()\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", " 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", " #create scaler\n", " self._min_max()\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", " state = self._get_scaled_state(state)\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 = random.randrange(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", " next_state = self._get_scaled_state(next_state)\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]} \")\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 every 100 steps \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.load_weights(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_weights(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": 58, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model: \"sequential_36\"\n", "_________________________________________________________________\n", " Layer (type) Output Shape Param # \n", "=================================================================\n", " dense_144 (Dense) (None, 512) 2560 \n", " \n", " dense_145 (Dense) (None, 256) 131328 \n", " \n", " dense_146 (Dense) (None, 128) 32896 \n", " \n", " dense_147 (Dense) (None, 2) 258 \n", " \n", "=================================================================\n", "Total params: 167,042\n", "Trainable params: 167,042\n", "Non-trainable params: 0\n", "_________________________________________________________________\n", "epsilon:1.0 step:15 episode:1 last_score 0 \n", "epsilon:1.0 step:20 episode:1 last_score 0 \n", "epsilon:0.95 step:25 episode:1 last_score 0 \n", "epsilon:0.95 step:30 episode:2 last_score 26.0 \n", "epsilon:0.95 step:35 episode:2 last_score 26.0 \n", "epsilon:0.95 step:40 episode:3 last_score 11.0 \n", "epsilon:0.9025 step:45 episode:3 last_score 11.0 \n", "epsilon:0.9025 step:50 episode:3 last_score 11.0 \n", "epsilon:0.9025 step:55 episode:3 last_score 11.0 \n", "epsilon:0.9025 step:60 episode:4 last_score 21.0 \n", "epsilon:0.8573749999999999 step:65 episode:4 last_score 21.0 \n", "epsilon:0.8573749999999999 step:70 episode:4 last_score 21.0 \n", "epsilon:0.8573749999999999 step:75 episode:5 last_score 13.0 \n", "epsilon:0.8573749999999999 step:80 episode:5 last_score 13.0 \n", "epsilon:0.8145062499999999 step:85 episode:5 last_score 13.0 \n", "epsilon:0.8145062499999999 step:90 episode:5 last_score 13.0 \n", "epsilon:0.8145062499999999 step:95 episode:6 last_score 21.0 \n", "epsilon:0.8145062499999999 step:100 episode:6 last_score 21.0 \n", "epsilon:0.7737809374999999 step:105 episode:7 last_score 11.0 \n", "epsilon:0.7737809374999999 step:110 episode:7 last_score 11.0 \n", "epsilon:0.7737809374999999 step:115 episode:7 last_score 11.0 \n", "epsilon:0.7737809374999999 step:120 episode:8 last_score 13.0 \n", "epsilon:0.7350918906249998 step:125 episode:8 last_score 13.0 \n", "epsilon:0.7350918906249998 step:130 episode:8 last_score 13.0 \n", "epsilon:0.7350918906249998 step:135 episode:8 last_score 13.0 \n", "epsilon:0.7350918906249998 step:140 episode:8 last_score 13.0 \n", "epsilon:0.6983372960937497 step:145 episode:8 last_score 13.0 \n", "epsilon:0.6983372960937497 step:150 episode:8 last_score 13.0 \n", "epsilon:0.6983372960937497 step:155 episode:8 last_score 13.0 \n", "epsilon:0.6983372960937497 step:160 episode:9 last_score 40.0 \n", "epsilon:0.6634204312890623 step:165 episode:9 last_score 40.0 \n", "epsilon:0.6634204312890623 step:170 episode:9 last_score 40.0 \n", "epsilon:0.6634204312890623 step:175 episode:10 last_score 15.0 \n", "epsilon:0.6634204312890623 step:180 episode:10 last_score 15.0 \n", "epsilon:0.6302494097246091 step:185 episode:10 last_score 15.0 \n", "epsilon:0.6302494097246091 step:190 episode:10 last_score 15.0 \n", "epsilon:0.6302494097246091 step:195 episode:10 last_score 15.0 \n", "epsilon:0.6302494097246091 step:200 episode:11 last_score 27.0 \n", "epsilon:0.5987369392383786 step:205 episode:11 last_score 27.0 \n", "epsilon:0.5987369392383786 step:210 episode:12 last_score 8.0 \n", "epsilon:0.5987369392383786 step:215 episode:12 last_score 8.0 \n", "epsilon:0.5987369392383786 step:220 episode:13 last_score 12.0 \n", "epsilon:0.5688000922764596 step:225 episode:13 last_score 12.0 \n", "epsilon:0.5688000922764596 step:230 episode:13 last_score 12.0 \n", "epsilon:0.5688000922764596 step:235 episode:14 last_score 13.0 \n", "epsilon:0.5688000922764596 step:240 episode:14 last_score 13.0 \n", "epsilon:0.5403600876626365 step:245 episode:15 last_score 12.0 \n", "epsilon:0.5403600876626365 step:250 episode:15 last_score 12.0 \n", "epsilon:0.5403600876626365 step:255 episode:15 last_score 12.0 \n", "epsilon:0.5403600876626365 step:260 episode:16 last_score 15.0 \n", "epsilon:0.5133420832795047 step:265 episode:16 last_score 15.0 \n", "epsilon:0.5133420832795047 step:270 episode:16 last_score 15.0 \n", "epsilon:0.5133420832795047 step:275 episode:16 last_score 15.0 \n", "epsilon:0.5133420832795047 step:280 episode:16 last_score 15.0 \n", "epsilon:0.48767497911552943 step:285 episode:17 last_score 23.0 \n", "epsilon:0.48767497911552943 step:290 episode:17 last_score 23.0 \n", "epsilon:0.48767497911552943 step:295 episode:18 last_score 9.0 \n", "epsilon:0.48767497911552943 step:300 episode:19 last_score 9.0 \n", "epsilon:0.46329123015975293 step:305 episode:19 last_score 9.0 \n", "epsilon:0.46329123015975293 step:310 episode:19 last_score 9.0 \n", "epsilon:0.46329123015975293 step:315 episode:20 last_score 14.0 \n", "epsilon:0.46329123015975293 step:320 episode:20 last_score 14.0 \n", "epsilon:0.44012666865176525 step:325 episode:20 last_score 14.0 \n", "epsilon:0.44012666865176525 step:330 episode:20 last_score 14.0 \n", "epsilon:0.44012666865176525 step:335 episode:21 last_score 21.0 \n", "epsilon:0.44012666865176525 step:340 episode:21 last_score 21.0 \n", "epsilon:0.41812033521917696 step:345 episode:21 last_score 21.0 \n", "epsilon:0.41812033521917696 step:350 episode:22 last_score 12.0 \n", "epsilon:0.41812033521917696 step:355 episode:22 last_score 12.0 \n", "epsilon:0.41812033521917696 step:360 episode:23 last_score 9.0 \n", "epsilon:0.3972143184582181 step:365 episode:23 last_score 9.0 \n", "epsilon:0.3972143184582181 step:370 episode:24 last_score 14.0 \n", "epsilon:0.3972143184582181 step:375 episode:24 last_score 14.0 \n", "epsilon:0.3972143184582181 step:380 episode:25 last_score 10.0 \n", "epsilon:0.37735360253530714 step:385 episode:25 last_score 10.0 \n", "epsilon:0.37735360253530714 step:390 episode:25 last_score 10.0 \n", "epsilon:0.37735360253530714 step:395 episode:25 last_score 10.0 \n", "epsilon:0.37735360253530714 step:400 episode:26 last_score 20.0 \n", "epsilon:0.35848592240854177 step:405 episode:26 last_score 20.0 \n", "epsilon:0.35848592240854177 step:410 episode:27 last_score 9.0 \n", "epsilon:0.35848592240854177 step:415 episode:27 last_score 9.0 \n", "epsilon:0.35848592240854177 step:420 episode:28 last_score 10.0 \n", "epsilon:0.34056162628811465 step:425 episode:28 last_score 10.0 \n", "epsilon:0.34056162628811465 step:430 episode:28 last_score 10.0 \n", "epsilon:0.34056162628811465 step:435 episode:29 last_score 14.0 \n", "epsilon:0.34056162628811465 step:440 episode:29 last_score 14.0 \n", "epsilon:0.3235335449737089 step:445 episode:30 last_score 11.0 \n", "epsilon:0.3235335449737089 step:450 episode:30 last_score 11.0 \n", "epsilon:0.3235335449737089 step:455 episode:31 last_score 10.0 \n", "epsilon:0.3235335449737089 step:460 episode:31 last_score 10.0 \n", "epsilon:0.30735686772502346 step:465 episode:31 last_score 10.0 \n", "epsilon:0.30735686772502346 step:470 episode:32 last_score 12.0 \n", "epsilon:0.30735686772502346 step:475 episode:33 last_score 8.0 \n", "epsilon:0.30735686772502346 step:480 episode:33 last_score 8.0 \n", "epsilon:0.2919890243387723 step:485 episode:34 last_score 10.0 \n", "epsilon:0.2919890243387723 step:490 episode:34 last_score 10.0 \n", "epsilon:0.2919890243387723 step:495 episode:35 last_score 9.0 \n", "epsilon:0.2919890243387723 step:500 episode:35 last_score 9.0 \n", "epsilon:0.27738957312183365 step:505 episode:36 last_score 10.0 \n", "epsilon:0.27738957312183365 step:510 episode:36 last_score 10.0 \n", "epsilon:0.27738957312183365 step:515 episode:37 last_score 10.0 \n", "epsilon:0.27738957312183365 step:520 episode:37 last_score 10.0 \n", "epsilon:0.263520094465742 step:525 episode:38 last_score 9.0 \n", "epsilon:0.263520094465742 step:530 episode:38 last_score 9.0 \n", "epsilon:0.263520094465742 step:535 episode:39 last_score 10.0 \n", "epsilon:0.263520094465742 step:540 episode:39 last_score 10.0 \n", "epsilon:0.25034408974245487 step:545 episode:40 last_score 10.0 \n", "epsilon:0.25034408974245487 step:550 episode:40 last_score 10.0 \n", "epsilon:0.25034408974245487 step:555 episode:40 last_score 10.0 \n", "epsilon:0.25034408974245487 step:560 episode:41 last_score 14.0 \n", "epsilon:0.2378268852553321 step:565 episode:41 last_score 14.0 \n", "epsilon:0.2378268852553321 step:570 episode:42 last_score 10.0 \n", "epsilon:0.2378268852553321 step:575 episode:43 last_score 9.0 \n", "epsilon:0.2378268852553321 step:580 episode:43 last_score 9.0 \n", "epsilon:0.2259355409925655 step:585 episode:43 last_score 9.0 \n", "epsilon:0.2259355409925655 step:590 episode:44 last_score 13.0 \n", "epsilon:0.2259355409925655 step:595 episode:44 last_score 13.0 \n", "epsilon:0.2259355409925655 step:600 episode:45 last_score 11.0 \n", "epsilon:0.2146387639429372 step:605 episode:45 last_score 11.0 \n", "epsilon:0.2146387639429372 step:610 episode:46 last_score 8.0 \n", "epsilon:0.2146387639429372 step:615 episode:46 last_score 8.0 \n", "epsilon:0.2146387639429372 step:620 episode:46 last_score 8.0 \n", "epsilon:0.20390682574579033 step:625 episode:47 last_score 14.0 \n", "epsilon:0.20390682574579033 step:630 episode:48 last_score 9.0 \n", "epsilon:0.20390682574579033 step:635 episode:48 last_score 9.0 \n", "epsilon:0.20390682574579033 step:640 episode:49 last_score 9.0 \n", "epsilon:0.1937114844585008 step:645 episode:49 last_score 9.0 \n", "epsilon:0.1937114844585008 step:650 episode:50 last_score 10.0 \n", "epsilon:0.1937114844585008 step:655 episode:50 last_score 10.0 \n", "epsilon:0.1937114844585008 step:660 episode:50 last_score 10.0 \n", "epsilon:0.18402591023557577 step:665 episode:51 last_score 12.0 \n", "epsilon:0.18402591023557577 step:670 episode:52 last_score 8.0 \n", "epsilon:0.18402591023557577 step:675 episode:52 last_score 8.0 \n", "epsilon:0.18402591023557577 step:680 episode:53 last_score 11.0 \n", "epsilon:0.17482461472379698 step:685 episode:53 last_score 11.0 \n", "epsilon:0.17482461472379698 step:690 episode:53 last_score 11.0 \n", "epsilon:0.17482461472379698 step:695 episode:54 last_score 15.0 \n", "epsilon:0.17482461472379698 step:700 episode:54 last_score 15.0 \n", "epsilon:0.16608338398760714 step:705 episode:55 last_score 10.0 \n", "epsilon:0.16608338398760714 step:710 episode:55 last_score 10.0 \n", "epsilon:0.16608338398760714 step:715 episode:56 last_score 10.0 \n", "epsilon:0.16608338398760714 step:720 episode:56 last_score 10.0 \n", "epsilon:0.15777921478822676 step:725 episode:56 last_score 10.0 \n", "epsilon:0.15777921478822676 step:730 episode:57 last_score 12.0 \n", "epsilon:0.15777921478822676 step:735 episode:57 last_score 12.0 \n", "epsilon:0.15777921478822676 step:740 episode:58 last_score 10.0 \n", "epsilon:0.14989025404881542 step:745 episode:58 last_score 10.0 \n", "epsilon:0.14989025404881542 step:750 episode:59 last_score 11.0 \n", "epsilon:0.14989025404881542 step:755 episode:59 last_score 11.0 \n", "epsilon:0.14989025404881542 step:760 episode:60 last_score 9.0 \n", "epsilon:0.14239574134637464 step:765 episode:60 last_score 9.0 \n", "epsilon:0.14239574134637464 step:770 episode:61 last_score 11.0 \n", "epsilon:0.14239574134637464 step:775 episode:61 last_score 11.0 \n", "epsilon:0.14239574134637464 step:780 episode:61 last_score 11.0 \n", "epsilon:0.1352759542790559 step:785 episode:62 last_score 14.0 \n", "epsilon:0.1352759542790559 step:790 episode:62 last_score 14.0 \n", "epsilon:0.1352759542790559 step:795 episode:63 last_score 12.0 \n", "epsilon:0.1352759542790559 step:800 episode:63 last_score 12.0 \n", "epsilon:0.1285121565651031 step:805 episode:63 last_score 12.0 \n", "epsilon:0.1285121565651031 step:810 episode:64 last_score 13.0 \n", "epsilon:0.1285121565651031 step:815 episode:64 last_score 13.0 \n", "epsilon:0.1285121565651031 step:820 episode:64 last_score 13.0 \n", "epsilon:0.12208654873684793 step:825 episode:65 last_score 14.0 \n", "epsilon:0.12208654873684793 step:830 episode:65 last_score 14.0 \n", "epsilon:0.12208654873684793 step:835 episode:66 last_score 10.0 \n", "epsilon:0.12208654873684793 step:840 episode:66 last_score 10.0 \n", "epsilon:0.11598222130000553 step:845 episode:67 last_score 14.0 \n", "epsilon:0.11598222130000553 step:850 episode:67 last_score 14.0 \n", "epsilon:0.11598222130000553 step:855 episode:67 last_score 14.0 \n", "epsilon:0.11598222130000553 step:860 episode:68 last_score 13.0 \n", "epsilon:0.11018311023500525 step:865 episode:68 last_score 13.0 \n", "epsilon:0.11018311023500525 step:870 episode:68 last_score 13.0 \n", "epsilon:0.11018311023500525 step:875 episode:69 last_score 15.0 \n", "epsilon:0.11018311023500525 step:880 episode:69 last_score 15.0 \n", "epsilon:0.10467395472325498 step:885 episode:70 last_score 11.0 \n", "epsilon:0.10467395472325498 step:890 episode:70 last_score 11.0 \n", "epsilon:0.10467395472325498 step:895 episode:70 last_score 11.0 \n", "epsilon:0.10467395472325498 step:900 episode:70 last_score 11.0 \n", "epsilon:0.09944025698709223 step:905 episode:71 last_score 18.0 \n", "epsilon:0.09944025698709223 step:910 episode:71 last_score 18.0 \n", "epsilon:0.09944025698709223 step:915 episode:71 last_score 18.0 \n", "epsilon:0.09944025698709223 step:920 episode:71 last_score 18.0 \n", "epsilon:0.09446824413773762 step:925 episode:72 last_score 22.0 \n", "epsilon:0.09446824413773762 step:930 episode:72 last_score 22.0 \n", "epsilon:0.09446824413773762 step:935 episode:72 last_score 22.0 \n", "epsilon:0.09446824413773762 step:940 episode:72 last_score 22.0 \n", "epsilon:0.08974483193085074 step:945 episode:72 last_score 22.0 \n", "epsilon:0.08974483193085074 step:950 episode:72 last_score 22.0 \n", "epsilon:0.08974483193085074 step:955 episode:72 last_score 22.0 \n", "epsilon:0.08974483193085074 step:960 episode:72 last_score 22.0 \n", "epsilon:0.0852575903343082 step:965 episode:72 last_score 22.0 \n", "epsilon:0.0852575903343082 step:970 episode:72 last_score 22.0 \n", "epsilon:0.0852575903343082 step:975 episode:72 last_score 22.0 \n", "epsilon:0.0852575903343082 step:980 episode:72 last_score 22.0 \n", "epsilon:0.08099471081759278 step:985 episode:72 last_score 22.0 \n", "epsilon:0.08099471081759278 step:990 episode:73 last_score 66.0 \n", "epsilon:0.08099471081759278 step:995 episode:73 last_score 66.0 \n", "epsilon:0.08099471081759278 step:1000 episode:73 last_score 66.0 \n", "epsilon:0.07694497527671314 step:1005 episode:73 last_score 66.0 \n", "epsilon:0.07694497527671314 step:1010 episode:73 last_score 66.0 \n", "epsilon:0.07694497527671314 step:1015 episode:73 last_score 66.0 \n", "epsilon:0.07694497527671314 step:1020 episode:73 last_score 66.0 \n", "epsilon:0.07309772651287748 step:1025 episode:73 last_score 66.0 \n", "epsilon:0.07309772651287748 step:1030 episode:73 last_score 66.0 \n", "epsilon:0.07309772651287748 step:1035 episode:73 last_score 66.0 \n", "epsilon:0.07309772651287748 step:1040 episode:73 last_score 66.0 \n", "epsilon:0.0694428401872336 step:1045 episode:73 last_score 66.0 \n", "epsilon:0.0694428401872336 step:1050 episode:73 last_score 66.0 \n", "epsilon:0.0694428401872336 step:1055 episode:73 last_score 66.0 \n", "epsilon:0.0694428401872336 step:1060 episode:73 last_score 66.0 \n", "epsilon:0.0659706981778719 step:1065 episode:74 last_score 74.0 \n", "epsilon:0.0659706981778719 step:1070 episode:74 last_score 74.0 \n", "epsilon:0.0659706981778719 step:1075 episode:74 last_score 74.0 \n", "epsilon:0.0659706981778719 step:1080 episode:74 last_score 74.0 \n", "epsilon:0.0626721632689783 step:1085 episode:74 last_score 74.0 \n", "epsilon:0.0626721632689783 step:1090 episode:74 last_score 74.0 \n", "epsilon:0.0626721632689783 step:1095 episode:74 last_score 74.0 \n", "epsilon:0.0626721632689783 step:1100 episode:74 last_score 74.0 \n", "epsilon:0.059538555105529384 step:1105 episode:74 last_score 74.0 \n", "epsilon:0.059538555105529384 step:1110 episode:74 last_score 74.0 \n", "epsilon:0.059538555105529384 step:1115 episode:75 last_score 47.0 \n", "epsilon:0.059538555105529384 step:1120 episode:75 last_score 47.0 \n", "epsilon:0.05656162735025291 step:1125 episode:75 last_score 47.0 \n", "epsilon:0.05656162735025291 step:1130 episode:75 last_score 47.0 \n", "epsilon:0.05656162735025291 step:1135 episode:75 last_score 47.0 \n", "epsilon:0.05656162735025291 step:1140 episode:75 last_score 47.0 \n", "epsilon:0.053733545982740265 step:1145 episode:75 last_score 47.0 \n", "epsilon:0.053733545982740265 step:1150 episode:75 last_score 47.0 \n", "epsilon:0.053733545982740265 step:1155 episode:75 last_score 47.0 \n", "epsilon:0.053733545982740265 step:1160 episode:75 last_score 47.0 \n", "epsilon:0.05104686868360325 step:1165 episode:75 last_score 47.0 \n", "epsilon:0.05104686868360325 step:1170 episode:75 last_score 47.0 \n", "epsilon:0.05104686868360325 step:1175 episode:75 last_score 47.0 \n", "epsilon:0.05104686868360325 step:1180 episode:75 last_score 47.0 \n", "epsilon:0.04849452524942309 step:1185 episode:75 last_score 47.0 \n", "epsilon:0.04849452524942309 step:1190 episode:75 last_score 47.0 \n", "epsilon:0.04849452524942309 step:1195 episode:75 last_score 47.0 \n", "epsilon:0.04849452524942309 step:1200 episode:75 last_score 47.0 \n", "epsilon:0.04606979898695193 step:1205 episode:76 last_score 91.0 \n", "epsilon:0.04606979898695193 step:1210 episode:76 last_score 91.0 \n", "epsilon:0.04606979898695193 step:1215 episode:76 last_score 91.0 \n", "epsilon:0.04606979898695193 step:1220 episode:76 last_score 91.0 \n", "epsilon:0.04376630903760433 step:1225 episode:76 last_score 91.0 \n", "epsilon:0.04376630903760433 step:1230 episode:76 last_score 91.0 \n", "epsilon:0.04376630903760433 step:1235 episode:76 last_score 91.0 \n", "epsilon:0.04376630903760433 step:1240 episode:76 last_score 91.0 \n", "epsilon:0.041577993585724116 step:1245 episode:76 last_score 91.0 \n", "epsilon:0.041577993585724116 step:1250 episode:76 last_score 91.0 \n", "epsilon:0.041577993585724116 step:1255 episode:76 last_score 91.0 \n", "epsilon:0.041577993585724116 step:1260 episode:76 last_score 91.0 \n", "epsilon:0.03949909390643791 step:1265 episode:76 last_score 91.0 \n", "epsilon:0.03949909390643791 step:1270 episode:76 last_score 91.0 \n", "epsilon:0.03949909390643791 step:1275 episode:76 last_score 91.0 \n", "epsilon:0.03949909390643791 step:1280 episode:76 last_score 91.0 \n", "epsilon:0.03752413921111601 step:1285 episode:77 last_score 82.0 \n", "epsilon:0.03752413921111601 step:1290 episode:77 last_score 82.0 \n", "epsilon:0.03752413921111601 step:1295 episode:77 last_score 82.0 \n", "epsilon:0.03752413921111601 step:1300 episode:77 last_score 82.0 \n", "epsilon:0.03564793225056021 step:1305 episode:77 last_score 82.0 \n", "epsilon:0.03564793225056021 step:1310 episode:77 last_score 82.0 \n", "epsilon:0.03564793225056021 step:1315 episode:77 last_score 82.0 \n", "epsilon:0.03564793225056021 step:1320 episode:77 last_score 82.0 \n", "epsilon:0.0338655356380322 step:1325 episode:77 last_score 82.0 \n", "epsilon:0.0338655356380322 step:1330 episode:77 last_score 82.0 \n", "epsilon:0.0338655356380322 step:1335 episode:78 last_score 49.0 \n", "epsilon:0.0338655356380322 step:1340 episode:78 last_score 49.0 \n", "epsilon:0.032172258856130585 step:1345 episode:78 last_score 49.0 \n", "epsilon:0.032172258856130585 step:1350 episode:78 last_score 49.0 \n", "epsilon:0.032172258856130585 step:1355 episode:78 last_score 49.0 \n", "epsilon:0.032172258856130585 step:1360 episode:78 last_score 49.0 \n", "epsilon:0.030563645913324056 step:1365 episode:79 last_score 28.0 \n", "epsilon:0.030563645913324056 step:1370 episode:79 last_score 28.0 \n", "epsilon:0.030563645913324056 step:1375 episode:79 last_score 28.0 \n", "epsilon:0.030563645913324056 step:1380 episode:79 last_score 28.0 \n", "epsilon:0.029035463617657853 step:1385 episode:79 last_score 28.0 \n", "epsilon:0.029035463617657853 step:1390 episode:79 last_score 28.0 \n", "epsilon:0.029035463617657853 step:1395 episode:79 last_score 28.0 \n", "epsilon:0.029035463617657853 step:1400 episode:80 last_score 36.0 \n", "epsilon:0.027583690436774957 step:1405 episode:80 last_score 36.0 \n", "epsilon:0.027583690436774957 step:1410 episode:80 last_score 36.0 \n", "epsilon:0.027583690436774957 step:1415 episode:80 last_score 36.0 \n", "epsilon:0.027583690436774957 step:1420 episode:80 last_score 36.0 \n", "epsilon:0.02620450591493621 step:1425 episode:80 last_score 36.0 \n", "epsilon:0.02620450591493621 step:1430 episode:80 last_score 36.0 \n", "epsilon:0.02620450591493621 step:1435 episode:80 last_score 36.0 \n", "epsilon:0.02620450591493621 step:1440 episode:80 last_score 36.0 \n", "epsilon:0.0248942806191894 step:1445 episode:80 last_score 36.0 \n", "epsilon:0.0248942806191894 step:1450 episode:80 last_score 36.0 \n", "epsilon:0.0248942806191894 step:1455 episode:80 last_score 36.0 \n", "epsilon:0.0248942806191894 step:1460 episode:81 last_score 60.0 \n", "epsilon:0.023649566588229927 step:1465 episode:81 last_score 60.0 \n", "epsilon:0.023649566588229927 step:1470 episode:81 last_score 60.0 \n", "epsilon:0.023649566588229927 step:1475 episode:81 last_score 60.0 \n", "epsilon:0.023649566588229927 step:1480 episode:81 last_score 60.0 \n", "epsilon:0.022467088258818428 step:1485 episode:81 last_score 60.0 \n", "epsilon:0.022467088258818428 step:1490 episode:82 last_score 32.0 \n", "epsilon:0.022467088258818428 step:1495 episode:82 last_score 32.0 \n", "epsilon:0.022467088258818428 step:1500 episode:82 last_score 32.0 \n", "epsilon:0.021343733845877507 step:1505 episode:82 last_score 32.0 \n", "epsilon:0.021343733845877507 step:1510 episode:82 last_score 32.0 \n", "epsilon:0.021343733845877507 step:1515 episode:82 last_score 32.0 \n", "epsilon:0.021343733845877507 step:1520 episode:82 last_score 32.0 \n", "epsilon:0.02027654715358363 step:1525 episode:83 last_score 32.0 \n", "epsilon:0.02027654715358363 step:1530 episode:83 last_score 32.0 \n", "epsilon:0.02027654715358363 step:1535 episode:83 last_score 32.0 \n", "epsilon:0.02027654715358363 step:1540 episode:83 last_score 32.0 \n", "epsilon:0.019262719795904448 step:1545 episode:83 last_score 32.0 \n", "epsilon:0.019262719795904448 step:1550 episode:83 last_score 32.0 \n", "epsilon:0.019262719795904448 step:1555 episode:83 last_score 32.0 \n", "epsilon:0.019262719795904448 step:1560 episode:83 last_score 32.0 \n", "epsilon:0.018299583806109226 step:1565 episode:83 last_score 32.0 \n", "epsilon:0.018299583806109226 step:1570 episode:83 last_score 32.0 \n", "epsilon:0.018299583806109226 step:1575 episode:83 last_score 32.0 \n", "epsilon:0.018299583806109226 step:1580 episode:84 last_score 57.0 \n", "epsilon:0.017384604615803764 step:1585 episode:84 last_score 57.0 \n", "epsilon:0.017384604615803764 step:1590 episode:84 last_score 57.0 \n", "epsilon:0.017384604615803764 step:1595 episode:84 last_score 57.0 \n", "epsilon:0.017384604615803764 step:1600 episode:84 last_score 57.0 \n", "epsilon:0.016515374385013576 step:1605 episode:84 last_score 57.0 \n", "epsilon:0.016515374385013576 step:1610 episode:84 last_score 57.0 \n", "epsilon:0.016515374385013576 step:1615 episode:84 last_score 57.0 \n", "epsilon:0.016515374385013576 step:1620 episode:84 last_score 57.0 \n", "epsilon:0.015689605665762895 step:1625 episode:84 last_score 57.0 \n", "epsilon:0.015689605665762895 step:1630 episode:84 last_score 57.0 \n", "epsilon:0.015689605665762895 step:1635 episode:84 last_score 57.0 \n", "epsilon:0.015689605665762895 step:1640 episode:84 last_score 57.0 \n", "epsilon:0.01490512538247475 step:1645 episode:84 last_score 57.0 \n", "epsilon:0.01490512538247475 step:1650 episode:84 last_score 57.0 \n", "epsilon:0.01490512538247475 step:1655 episode:84 last_score 57.0 \n", "epsilon:0.01490512538247475 step:1660 episode:84 last_score 57.0 \n", "epsilon:0.014159869113351011 step:1665 episode:85 last_score 86.0 \n", "epsilon:0.014159869113351011 step:1670 episode:85 last_score 86.0 \n", "epsilon:0.014159869113351011 step:1675 episode:85 last_score 86.0 \n", "epsilon:0.014159869113351011 step:1680 episode:85 last_score 86.0 \n", "epsilon:0.01345187565768346 step:1685 episode:85 last_score 86.0 \n", "epsilon:0.01345187565768346 step:1690 episode:85 last_score 86.0 \n", "epsilon:0.01345187565768346 step:1695 episode:85 last_score 86.0 \n", "epsilon:0.01345187565768346 step:1700 episode:85 last_score 86.0 \n", "epsilon:0.012779281874799287 step:1705 episode:86 last_score 41.0 \n", "epsilon:0.012779281874799287 step:1710 episode:86 last_score 41.0 \n", "epsilon:0.012779281874799287 step:1715 episode:86 last_score 41.0 \n", "epsilon:0.012779281874799287 step:1720 episode:86 last_score 41.0 \n", "epsilon:0.012140317781059323 step:1725 episode:86 last_score 41.0 \n", "epsilon:0.012140317781059323 step:1730 episode:86 last_score 41.0 \n", "epsilon:0.012140317781059323 step:1735 episode:86 last_score 41.0 \n", "epsilon:0.012140317781059323 step:1740 episode:86 last_score 41.0 \n", "epsilon:0.011533301892006355 step:1745 episode:86 last_score 41.0 \n", "epsilon:0.011533301892006355 step:1750 episode:86 last_score 41.0 \n", "epsilon:0.011533301892006355 step:1755 episode:86 last_score 41.0 \n", "epsilon:0.011533301892006355 step:1760 episode:86 last_score 41.0 \n", "epsilon:0.010956636797406038 step:1765 episode:87 last_score 59.0 \n", "epsilon:0.010956636797406038 step:1770 episode:87 last_score 59.0 \n", "epsilon:0.010956636797406038 step:1775 episode:87 last_score 59.0 \n", "epsilon:0.010956636797406038 step:1780 episode:87 last_score 59.0 \n", "epsilon:0.010408804957535735 step:1785 episode:87 last_score 59.0 \n", "epsilon:0.010408804957535735 step:1790 episode:87 last_score 59.0 \n", "epsilon:0.010408804957535735 step:1795 episode:87 last_score 59.0 \n", "epsilon:0.010408804957535735 step:1800 episode:87 last_score 59.0 \n", "epsilon:0.009888364709658948 step:1805 episode:88 last_score 41.0 \n", "epsilon:0.009888364709658948 step:1810 episode:88 last_score 41.0 \n", "epsilon:0.009888364709658948 step:1815 episode:88 last_score 41.0 \n", "epsilon:0.009888364709658948 step:1820 episode:88 last_score 41.0 \n", "epsilon:0.009393946474176 step:1825 episode:88 last_score 41.0 \n", "epsilon:0.009393946474176 step:1830 episode:88 last_score 41.0 \n", "epsilon:0.009393946474176 step:1835 episode:88 last_score 41.0 \n", "epsilon:0.009393946474176 step:1840 episode:89 last_score 34.0 \n", "epsilon:0.0089242491504672 step:1845 episode:89 last_score 34.0 \n", "epsilon:0.0089242491504672 step:1850 episode:89 last_score 34.0 \n", "epsilon:0.0089242491504672 step:1855 episode:89 last_score 34.0 \n", "epsilon:0.0089242491504672 step:1860 episode:89 last_score 34.0 \n", "epsilon:0.008478036692943839 step:1865 episode:89 last_score 34.0 \n", "epsilon:0.008478036692943839 step:1870 episode:89 last_score 34.0 \n", "epsilon:0.008478036692943839 step:1875 episode:90 last_score 32.0 \n", "epsilon:0.008478036692943839 step:1880 episode:90 last_score 32.0 \n", "epsilon:0.008054134858296647 step:1885 episode:90 last_score 32.0 \n", "epsilon:0.008054134858296647 step:1890 episode:90 last_score 32.0 \n", "epsilon:0.008054134858296647 step:1895 episode:90 last_score 32.0 \n", "epsilon:0.008054134858296647 step:1900 episode:90 last_score 32.0 \n", "epsilon:0.0076514281153818135 step:1905 episode:90 last_score 32.0 \n", "epsilon:0.0076514281153818135 step:1910 episode:90 last_score 32.0 \n", "epsilon:0.0076514281153818135 step:1915 episode:91 last_score 44.0 \n", "epsilon:0.0076514281153818135 step:1920 episode:91 last_score 44.0 \n", "epsilon:0.0072688567096127225 step:1925 episode:91 last_score 44.0 \n", "epsilon:0.0072688567096127225 step:1930 episode:91 last_score 44.0 \n", "epsilon:0.0072688567096127225 step:1935 episode:91 last_score 44.0 \n", "epsilon:0.0072688567096127225 step:1940 episode:91 last_score 44.0 \n", "epsilon:0.006905413874132086 step:1945 episode:91 last_score 44.0 \n", "epsilon:0.006905413874132086 step:1950 episode:91 last_score 44.0 \n", "epsilon:0.006905413874132086 step:1955 episode:91 last_score 44.0 \n", "epsilon:0.006905413874132086 step:1960 episode:91 last_score 44.0 \n", "epsilon:0.006560143180425482 step:1965 episode:92 last_score 46.0 \n", "epsilon:0.006560143180425482 step:1970 episode:92 last_score 46.0 \n", "epsilon:0.006560143180425482 step:1975 episode:92 last_score 46.0 \n", "epsilon:0.006560143180425482 step:1980 episode:92 last_score 46.0 \n", "epsilon:0.0062321360214042075 step:1985 episode:92 last_score 46.0 \n", "epsilon:0.0062321360214042075 step:1990 episode:92 last_score 46.0 \n", "epsilon:0.0062321360214042075 step:1995 episode:92 last_score 46.0 \n", "epsilon:0.0062321360214042075 step:2000 episode:92 last_score 46.0 \n", "epsilon:0.005920529220333997 step:2005 episode:92 last_score 46.0 \n", "epsilon:0.005920529220333997 step:2010 episode:92 last_score 46.0 \n", "epsilon:0.005920529220333997 step:2015 episode:92 last_score 46.0 \n", "epsilon:0.005920529220333997 step:2020 episode:92 last_score 46.0 \n", "epsilon:0.0056245027593172965 step:2025 episode:92 last_score 46.0 \n", "epsilon:0.0056245027593172965 step:2030 episode:92 last_score 46.0 \n", "epsilon:0.0056245027593172965 step:2035 episode:93 last_score 71.0 \n", "epsilon:0.0056245027593172965 step:2040 episode:93 last_score 71.0 \n", "epsilon:0.005343277621351432 step:2045 episode:93 last_score 71.0 \n", "epsilon:0.005343277621351432 step:2050 episode:93 last_score 71.0 \n", "epsilon:0.005343277621351432 step:2055 episode:93 last_score 71.0 \n", "epsilon:0.005343277621351432 step:2060 episode:93 last_score 71.0 \n", "epsilon:0.0050761137402838595 step:2065 episode:93 last_score 71.0 \n", "epsilon:0.0050761137402838595 step:2070 episode:93 last_score 71.0 \n", "epsilon:0.0050761137402838595 step:2075 episode:93 last_score 71.0 \n", "epsilon:0.0050761137402838595 step:2080 episode:93 last_score 71.0 \n", "epsilon:0.004822308053269666 step:2085 episode:93 last_score 71.0 \n", "epsilon:0.004822308053269666 step:2090 episode:93 last_score 71.0 \n", "epsilon:0.004822308053269666 step:2095 episode:93 last_score 71.0 \n", "epsilon:0.004822308053269666 step:2100 episode:93 last_score 71.0 \n", "epsilon:0.004581192650606183 step:2105 episode:93 last_score 71.0 \n", "epsilon:0.004581192650606183 step:2110 episode:93 last_score 71.0 \n", "epsilon:0.004581192650606183 step:2115 episode:93 last_score 71.0 \n", "epsilon:0.004581192650606183 step:2120 episode:93 last_score 71.0 \n", "epsilon:0.0043521330180758735 step:2125 episode:93 last_score 71.0 \n", "epsilon:0.0043521330180758735 step:2130 episode:93 last_score 71.0 \n", "epsilon:0.0043521330180758735 step:2135 episode:93 last_score 71.0 \n", "epsilon:0.0043521330180758735 step:2140 episode:93 last_score 71.0 \n", "epsilon:0.0041345263671720795 step:2145 episode:93 last_score 71.0 \n", "epsilon:0.0041345263671720795 step:2150 episode:93 last_score 71.0 \n", "epsilon:0.0041345263671720795 step:2155 episode:93 last_score 71.0 \n", "epsilon:0.0041345263671720795 step:2160 episode:93 last_score 71.0 \n", "epsilon:0.003927800048813475 step:2165 episode:93 last_score 71.0 \n", "epsilon:0.003927800048813475 step:2170 episode:93 last_score 71.0 \n", "epsilon:0.003927800048813475 step:2175 episode:93 last_score 71.0 \n", "epsilon:0.003927800048813475 step:2180 episode:94 last_score 146.0 \n", "epsilon:0.0037314100463728015 step:2185 episode:94 last_score 146.0 \n", "epsilon:0.0037314100463728015 step:2190 episode:94 last_score 146.0 \n", "epsilon:0.0037314100463728015 step:2195 episode:94 last_score 146.0 \n", "epsilon:0.0037314100463728015 step:2200 episode:94 last_score 146.0 \n", "epsilon:0.0035448395440541612 step:2205 episode:94 last_score 146.0 \n", "epsilon:0.0035448395440541612 step:2210 episode:94 last_score 146.0 \n", "epsilon:0.0035448395440541612 step:2215 episode:95 last_score 35.0 \n", "epsilon:0.0035448395440541612 step:2220 episode:95 last_score 35.0 \n", "epsilon:0.003367597566851453 step:2225 episode:95 last_score 35.0 \n", "epsilon:0.003367597566851453 step:2230 episode:95 last_score 35.0 \n", "epsilon:0.003367597566851453 step:2235 episode:95 last_score 35.0 \n", "epsilon:0.003367597566851453 step:2240 episode:95 last_score 35.0 \n", "epsilon:0.00319921768850888 step:2245 episode:95 last_score 35.0 \n", "epsilon:0.00319921768850888 step:2250 episode:95 last_score 35.0 \n", "epsilon:0.00319921768850888 step:2255 episode:95 last_score 35.0 \n", "epsilon:0.00319921768850888 step:2260 episode:96 last_score 46.0 \n", "epsilon:0.003039256804083436 step:2265 episode:96 last_score 46.0 \n", "epsilon:0.003039256804083436 step:2270 episode:96 last_score 46.0 \n", "epsilon:0.003039256804083436 step:2275 episode:96 last_score 46.0 \n", "epsilon:0.003039256804083436 step:2280 episode:96 last_score 46.0 \n", "epsilon:0.0028872939638792637 step:2285 episode:96 last_score 46.0 \n", "epsilon:0.0028872939638792637 step:2290 episode:96 last_score 46.0 \n", "epsilon:0.0028872939638792637 step:2295 episode:96 last_score 46.0 \n", "epsilon:0.0028872939638792637 step:2300 episode:97 last_score 40.0 \n", "epsilon:0.0027429292656853004 step:2305 episode:97 last_score 40.0 \n", "epsilon:0.0027429292656853004 step:2310 episode:97 last_score 40.0 \n", "epsilon:0.0027429292656853004 step:2315 episode:97 last_score 40.0 \n", "epsilon:0.0027429292656853004 step:2320 episode:97 last_score 40.0 \n", "epsilon:0.0026057828024010354 step:2325 episode:97 last_score 40.0 \n", "epsilon:0.0026057828024010354 step:2330 episode:97 last_score 40.0 \n", "epsilon:0.0026057828024010354 step:2335 episode:97 last_score 40.0 \n", "epsilon:0.0026057828024010354 step:2340 episode:97 last_score 40.0 \n", "epsilon:0.0024754936622809836 step:2345 episode:97 last_score 40.0 \n", "epsilon:0.0024754936622809836 step:2350 episode:97 last_score 40.0 \n", "epsilon:0.0024754936622809836 step:2355 episode:97 last_score 40.0 \n", "epsilon:0.0024754936622809836 step:2360 episode:97 last_score 40.0 \n", "epsilon:0.002351718979166934 step:2365 episode:97 last_score 40.0 \n", "epsilon:0.002351718979166934 step:2370 episode:97 last_score 40.0 \n", "epsilon:0.002351718979166934 step:2375 episode:98 last_score 74.0 \n", "epsilon:0.002351718979166934 step:2380 episode:98 last_score 74.0 \n", "epsilon:0.0022341330302085875 step:2385 episode:98 last_score 74.0 \n", "epsilon:0.0022341330302085875 step:2390 episode:98 last_score 74.0 \n", "epsilon:0.0022341330302085875 step:2395 episode:98 last_score 74.0 \n", "epsilon:0.0022341330302085875 step:2400 episode:98 last_score 74.0 \n", "epsilon:0.002122426378698158 step:2405 episode:98 last_score 74.0 \n", "epsilon:0.002122426378698158 step:2410 episode:98 last_score 74.0 \n", "epsilon:0.002122426378698158 step:2415 episode:98 last_score 74.0 \n", "epsilon:0.002122426378698158 step:2420 episode:98 last_score 74.0 \n", "epsilon:0.0020163050597632503 step:2425 episode:98 last_score 74.0 \n", "epsilon:0.0020163050597632503 step:2430 episode:98 last_score 74.0 \n", "epsilon:0.0020163050597632503 step:2435 episode:98 last_score 74.0 \n", "epsilon:0.0020163050597632503 step:2440 episode:98 last_score 74.0 \n", "epsilon:0.0019154898067750877 step:2445 episode:98 last_score 74.0 \n", "epsilon:0.0019154898067750877 step:2450 episode:98 last_score 74.0 \n", "epsilon:0.0019154898067750877 step:2455 episode:98 last_score 74.0 \n", "epsilon:0.0019154898067750877 step:2460 episode:98 last_score 74.0 \n", "epsilon:0.0018197153164363333 step:2465 episode:98 last_score 74.0 \n", "epsilon:0.0018197153164363333 step:2470 episode:98 last_score 74.0 \n", "epsilon:0.0018197153164363333 step:2475 episode:98 last_score 74.0 \n", "epsilon:0.0018197153164363333 step:2480 episode:99 last_score 105.0 \n", "epsilon:0.0017287295506145165 step:2485 episode:99 last_score 105.0 \n", "epsilon:0.0017287295506145165 step:2490 episode:99 last_score 105.0 \n", "epsilon:0.0017287295506145165 step:2495 episode:99 last_score 105.0 \n", "epsilon:0.0017287295506145165 step:2500 episode:99 last_score 105.0 \n", "epsilon:0.0016422930730837905 step:2505 episode:99 last_score 105.0 \n", "epsilon:0.0016422930730837905 step:2510 episode:99 last_score 105.0 \n", "epsilon:0.0016422930730837905 step:2515 episode:99 last_score 105.0 \n", "epsilon:0.0016422930730837905 step:2520 episode:99 last_score 105.0 \n", "epsilon:0.0015601784194296008 step:2525 episode:99 last_score 105.0 \n", "epsilon:0.0015601784194296008 step:2530 episode:99 last_score 105.0 \n", "epsilon:0.0015601784194296008 step:2535 episode:99 last_score 105.0 \n", "epsilon:0.0015601784194296008 step:2540 episode:99 last_score 105.0 \n", "epsilon:0.0014821694984581207 step:2545 episode:99 last_score 105.0 \n", "epsilon:0.0014821694984581207 step:2550 episode:99 last_score 105.0 \n", "epsilon:0.0014821694984581207 step:2555 episode:99 last_score 105.0 \n", "epsilon:0.0014821694984581207 step:2560 episode:100 last_score 79.0 \n", "epsilon:0.0014080610235352145 step:2565 episode:100 last_score 79.0 \n", "epsilon:0.0014080610235352145 step:2570 episode:100 last_score 79.0 \n", "epsilon:0.0014080610235352145 step:2575 episode:100 last_score 79.0 \n", "epsilon:0.0014080610235352145 step:2580 episode:100 last_score 79.0 \n", "epsilon:0.0013376579723584536 step:2585 episode:100 last_score 79.0 \n", "epsilon:0.0013376579723584536 step:2590 episode:100 last_score 79.0 \n", "epsilon:0.0013376579723584536 step:2595 episode:100 last_score 79.0 \n", "epsilon:0.0013376579723584536 step:2600 episode:100 last_score 79.0 \n", "epsilon:0.0012707750737405309 step:2605 episode:100 last_score 79.0 \n", "epsilon:0.0012707750737405309 step:2610 episode:100 last_score 79.0 \n", "epsilon:0.0012707750737405309 step:2615 episode:100 last_score 79.0 \n", "epsilon:0.0012707750737405309 step:2620 episode:100 last_score 79.0 \n", "epsilon:0.0012072363200535043 step:2625 episode:100 last_score 79.0 \n", "epsilon:0.0012072363200535043 step:2630 episode:100 last_score 79.0 \n", "epsilon:0.0012072363200535043 step:2635 episode:100 last_score 79.0 \n", "epsilon:0.0012072363200535043 step:2640 episode:100 last_score 79.0 \n", "epsilon:0.001146874504050829 step:2645 episode:100 last_score 79.0 \n", "epsilon:0.001146874504050829 step:2650 episode:101 last_score 92.0 \n", "epsilon:0.001146874504050829 step:2655 episode:101 last_score 92.0 \n", "epsilon:0.001146874504050829 step:2660 episode:101 last_score 92.0 \n", "epsilon:0.0010895307788482875 step:2665 episode:101 last_score 92.0 \n", "epsilon:0.0010895307788482875 step:2670 episode:101 last_score 92.0 \n", "epsilon:0.0010895307788482875 step:2675 episode:101 last_score 92.0 \n", "epsilon:0.0010895307788482875 step:2680 episode:101 last_score 92.0 \n", "epsilon:0.001035054239905873 step:2685 episode:101 last_score 92.0 \n", "epsilon:0.001035054239905873 step:2690 episode:101 last_score 92.0 \n", "epsilon:0.001035054239905873 step:2695 episode:101 last_score 92.0 \n", "epsilon:0.001035054239905873 step:2700 episode:101 last_score 92.0 \n", "epsilon:0.0009833015279105794 step:2705 episode:101 last_score 92.0 \n", "epsilon:0.0009833015279105794 step:2710 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2715 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2720 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2725 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2730 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2735 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2740 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2745 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2750 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2755 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2760 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2765 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2770 episode:102 last_score 61.0 \n", "epsilon:0.0009833015279105794 step:2775 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2780 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2785 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2790 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2795 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2800 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2805 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2810 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2815 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2820 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2825 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2830 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2835 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2840 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2845 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2850 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2855 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2860 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2865 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2870 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2875 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2880 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2885 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2890 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2895 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2900 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2905 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2910 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2915 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2920 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2925 episode:103 last_score 64.0 \n", "epsilon:0.0009833015279105794 step:2930 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2935 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2940 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2945 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2950 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2955 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2960 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2965 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2970 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2975 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2980 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2985 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2990 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:2995 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:3000 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:3005 episode:104 last_score 153.0 \n", "epsilon:0.0009833015279105794 step:3010 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3015 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3020 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3025 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3030 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3035 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3040 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3045 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3050 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3055 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3060 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3065 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3070 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3075 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3080 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3085 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3090 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3095 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3100 episode:105 last_score 82.0 \n", "epsilon:0.0009833015279105794 step:3105 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3110 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3115 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3120 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3125 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3130 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3135 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3140 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3145 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3150 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3155 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3160 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3165 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3170 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3175 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3180 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3185 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3190 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3195 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3200 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3205 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3210 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3215 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3220 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3225 episode:106 last_score 96.0 \n", "epsilon:0.0009833015279105794 step:3230 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3235 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3240 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3245 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3250 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3255 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3260 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3265 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3270 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3275 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3280 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3285 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3290 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3295 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3300 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3305 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3310 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3315 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3320 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3325 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3330 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3335 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3340 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3345 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3350 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3355 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3360 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3365 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3370 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3375 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3380 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3385 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3390 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3395 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3400 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3405 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3410 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3415 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3420 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3425 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3430 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3435 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3440 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3445 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3450 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3455 episode:107 last_score 121.0 \n", "epsilon:0.0009833015279105794 step:3460 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3465 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3470 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3475 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3480 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3485 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3490 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3495 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3500 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3505 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3510 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3515 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3520 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3525 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3530 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3535 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3540 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3545 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3550 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3555 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3560 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3565 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3570 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3575 episode:108 last_score 234.0 \n", "epsilon:0.0009833015279105794 step:3580 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3585 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3590 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3595 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3600 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3605 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3610 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3615 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3620 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3625 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3630 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3635 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3640 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3645 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3650 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3655 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3660 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3665 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3670 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3675 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3680 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3685 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3690 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3695 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3700 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3705 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3710 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3715 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3720 episode:109 last_score 118.0 \n", "epsilon:0.0009833015279105794 step:3725 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3730 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3735 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3740 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3745 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3750 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3755 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3760 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3765 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3770 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3775 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3780 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3785 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3790 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3795 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3800 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3805 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3810 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3815 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3820 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3825 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3830 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3835 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3840 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3845 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3850 episode:110 last_score 143.0 \n", "epsilon:0.0009833015279105794 step:3855 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3860 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3865 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3870 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3875 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3880 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3885 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3890 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3895 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3900 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3905 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3910 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3915 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3920 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3925 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3930 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3935 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3940 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3945 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3950 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3955 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3960 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3965 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3970 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3975 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3980 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3985 episode:111 last_score 131.0 \n", "epsilon:0.0009833015279105794 step:3990 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:3995 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4000 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4005 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4010 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4015 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4020 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4025 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4030 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4035 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4040 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4045 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4050 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4055 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4060 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4065 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4070 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4075 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4080 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4085 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4090 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4095 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4100 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4105 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4110 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4115 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4120 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4125 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4130 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4135 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4140 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4145 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4150 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4155 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4160 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4165 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4170 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4175 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4180 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4185 episode:112 last_score 137.0 \n", "epsilon:0.0009833015279105794 step:4190 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4195 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4200 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4205 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4210 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4215 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4220 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4225 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4230 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4235 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4240 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4245 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4250 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4255 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4260 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4265 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4270 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4275 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4280 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4285 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4290 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4295 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4300 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4305 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4310 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4315 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4320 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4325 episode:113 last_score 199.0 \n", "epsilon:0.0009833015279105794 step:4330 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4335 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4340 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4345 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4350 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4355 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4360 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4365 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4370 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4375 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4380 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4385 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4390 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4395 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4400 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4405 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4410 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4415 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4420 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4425 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4430 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4435 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4440 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4445 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4450 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4455 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4460 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4465 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4470 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4475 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4480 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4485 episode:114 last_score 139.0 \n", "epsilon:0.0009833015279105794 step:4490 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4495 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4500 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4505 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4510 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4515 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4520 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4525 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4530 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4535 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4540 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4545 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4550 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4555 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4560 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4565 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4570 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4575 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4580 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4585 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4590 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4595 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4600 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4605 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4610 episode:115 last_score 160.0 \n", "epsilon:0.0009833015279105794 step:4615 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4620 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4625 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4630 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4635 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4640 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4645 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4650 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4655 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4660 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4665 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4670 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4675 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4680 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4685 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4690 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4695 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4700 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4705 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4710 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4715 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4720 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4725 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4730 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4735 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4740 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4745 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4750 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4755 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4760 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4765 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4770 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4775 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4780 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4785 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4790 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4795 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4800 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4805 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4810 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4815 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4820 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4825 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4830 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4835 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4840 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4845 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4850 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4855 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4860 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4865 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4870 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4875 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4880 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4885 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4890 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4895 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4900 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4905 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4910 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4915 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4920 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4925 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4930 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4935 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4940 episode:116 last_score 125.0 \n", "epsilon:0.0009833015279105794 step:4945 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:4950 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:4955 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:4960 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:4965 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:4970 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:4975 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:4980 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:4985 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:4990 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:4995 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5000 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5005 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5010 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5015 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5020 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5025 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5030 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5035 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5040 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5045 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5050 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5055 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5060 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5065 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5070 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5075 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5080 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5085 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5090 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5095 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5100 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5105 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5110 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5115 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5120 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5125 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5130 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5135 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5140 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5145 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5150 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5155 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5160 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5165 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5170 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5175 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5180 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5185 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5190 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5195 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5200 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5205 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5210 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5215 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5220 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5225 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5230 episode:117 last_score 330.0 \n", "epsilon:0.0009833015279105794 step:5235 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5240 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5245 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5250 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5255 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5260 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5265 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5270 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5275 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5280 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5285 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5290 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5295 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5300 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5305 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5310 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5315 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5320 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5325 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5330 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5335 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5340 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5345 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5350 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5355 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5360 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5365 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5370 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5375 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5380 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5385 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5390 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5395 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5400 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5405 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5410 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5415 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5420 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5425 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5430 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5435 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5440 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5445 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5450 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5455 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5460 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5465 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5470 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5475 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5480 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5485 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5490 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5495 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5500 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5505 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5510 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5515 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5520 episode:118 last_score 292.0 \n", "epsilon:0.0009833015279105794 step:5525 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5530 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5535 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5540 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5545 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5550 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5555 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5560 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5565 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5570 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5575 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5580 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5585 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5590 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5595 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5600 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5605 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5610 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5615 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5620 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5625 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5630 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5635 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5640 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5645 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5650 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5655 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5660 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5665 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5670 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5675 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5680 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5685 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5690 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5695 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5700 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5705 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5710 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5715 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5720 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5725 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5730 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5735 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5740 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5745 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5750 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5755 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5760 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5765 episode:119 last_score 288.0 \n", "epsilon:0.0009833015279105794 step:5770 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5775 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5780 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5785 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5790 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5795 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5800 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5805 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5810 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5815 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5820 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5825 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5830 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5835 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5840 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5845 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5850 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5855 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5860 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5865 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5870 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5875 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5880 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5885 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5890 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5895 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5900 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5905 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5910 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5915 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5920 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5925 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5930 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5935 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5940 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5945 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5950 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5955 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5960 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5965 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5970 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5975 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5980 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5985 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5990 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:5995 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:6000 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:6005 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:6010 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:6015 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:6020 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:6025 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:6030 episode:120 last_score 244.0 \n", "epsilon:0.0009833015279105794 step:6035 episode:120 last_score 244.0 \n" ] } ], "source": [ "env = gym.make('CartPole-v1')\n", "\n", "model = DQN(env=env, replay_buffer_size=10_000, action_size=2)\n", "model.learn(total_steps=6_000)\n", "env.close()" ] }, { "cell_type": "code", "execution_count": 59, "metadata": {}, "outputs": [], "source": [ "model.save(\"./alt/DQN_v2.h5\")" ] }, { "cell_type": "code", "execution_count": 60, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model: \"sequential_38\"\n", "_________________________________________________________________\n", " Layer (type) Output Shape Param # \n", "=================================================================\n", " dense_152 (Dense) (None, 512) 2560 \n", " \n", " dense_153 (Dense) (None, 256) 131328 \n", " \n", " dense_154 (Dense) (None, 128) 32896 \n", " \n", " dense_155 (Dense) (None, 2) 258 \n", " \n", "=================================================================\n", "Total params: 167,042\n", "Trainable params: 167,042\n", "Non-trainable params: 0\n", "_________________________________________________________________\n", "Total reward 439.0\n" ] } ], "source": [ "eval_env = gym.make('CartPole-v1')\n", "model = DQN(env=eval_env, replay_buffer_size=10_000, action_size=2)\n", "model.load(\"./alt/DQN_v2.h5\")\n", "eval_env = wrappers.Monitor(eval_env, \"./alt/gym-results\", force=True)\n", "state = eval_env.reset()\n", "total_reward = 0\n", "for _ in range(1000):\n", " action = model.play(state)\n", " observation, reward, done, info = eval_env.step(action)\n", " total_reward +=reward\n", " state = observation\n", " if done: \n", " break\n", "print(f\"Total reward {total_reward}\")\n", "eval_env.close()" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[ 4.8000002e+00 0.0000000e+00 4.1887903e-01 0.0000000e+00]\n", " [-4.8000002e+00 0.0000000e+00 -4.1887903e-01 0.0000000e+00]\n", " [-4.5489166e-03 -2.4116948e-01 -4.1077949e-02 3.0230245e-01]\n", " ...\n", " [ 5.0607350e-02 1.7593256e-01 -8.8660561e-02 -4.2944443e-01]\n", " [ 5.4126002e-02 3.7219086e-01 -9.7249448e-02 -7.4870765e-01]\n", " [ 6.1569817e-02 5.6851023e-01 -1.1222360e-01 -1.0703416e+00]]\n", "Max [4.8 2.2215695 0.41887903 2.1663814 ]\n", "Min [-4.8 -1.4063605 -0.41887903 -2.5751066 ]\n", "[ 0.0172858 0.00332159 -0.03439883 0.01944862]\n", "[0.5018006 0.38856372 0.45893943 0.54720277]\n" ] } ], "source": [ "\n", "# def _min_max(env):\n", "# \"\"\"Run some steps to get data to do MINMAX scale \"\"\"\n", "# state_arr = []\n", "# state_arr.append(env.observation_space.high)\n", "# state_arr[0][1], state_arr[0][3] = 0,0\n", "# state_arr.append(env.observation_space.low)\n", "# state_arr[1][1], state_arr[1][3] = 0,0\n", "# state = env.reset()\n", "# for i in range(1000):\n", "# random_action = env.action_space.sample()\n", "# next_state, reward, done, info = env.step(random_action)\n", "# state_arr.append(next_state)\n", "# if done:\n", "# state = env.reset()\n", "\n", "# state_arr = np.array(state_arr)\n", "\n", "# print(state_arr)\n", "# scaler = MinMaxScaler()\n", "# scaler.fit(state_arr)\n", "# print(\"Max \",scaler.data_max_)\n", "# print(\"Min \", scaler.data_min_)\n", "# return scaler\n", "\n", "# env = gym.make('CartPole-v1')\n", "# scaler = _min_max(env)\n", "# state = env.reset()\n", "# print(state)\n", "# state = scaler.transform(state.reshape(1, -1)).flatten()\n", "# print(state)\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "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 }