Push to Hub

DQN-CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a083828360968689e221dbfbe7e216ee84b781bbe9fe95f6c2dba2b69743f9
+size 1106782

DQN-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.1.0

DQN-CartPole-v1/data

@@ -0,0 +1,130 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.dqn.policies",
+        "__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}",
+        "__doc__": "\n    Policy class with Q-Value Net and target net for DQN\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
+        "__init__": "<function DQNPolicy.__init__ at 0x7fccdbe3f1c0>",
+        "_build": "<function DQNPolicy._build at 0x7fccdbe3f250>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7fccdbe3f2e0>",
+        "forward": "<function DQNPolicy.forward at 0x7fccdbe3f370>",
+        "_predict": "<function DQNPolicy._predict at 0x7fccdbe3f400>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7fccdbe3f490>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7fccdbe3f520>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fccdbe4e900>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVUQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlChNAAFNAAFldS4=",
+        "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
+        "net_arch": [
+            256,
+            256
+        ]
+    },
+    "num_timesteps": 100000,
+    "_total_timesteps": 100000.0,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1698303731040257432,
+    "learning_rate": 0.0001,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAANLDsj1+YN4+BifMPObDCL+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAO7yqD1OZnU+/0z1PKuWgL6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 3751,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWV5QsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQGLAAAAAAACMAWyUS5aMAXSUR0BSRMOf/WDpdX2UKGgGR0BrQAAAAAAAaAdL2mgIR0BSUurELpiadX2UKGgGR0BLAAAAAAAAaAdLNmgIR0BSVmUfPompdX2UKGgGR0BugAAAAAAAaAdL9GgIR0BSZTMmnfl7dX2UKGgGR0A1AAAAAAAAaAdLFWgIR0BSZlLBbfP5dX2UKGgGR0BDAAAAAAAAaAdLJmgIR0BSaDbi6xxDdX2UKGgGR0A8AAAAAAAAaAdLHGgIR0BSacBdUsFudX2UKGgGR0A0AAAAAAAAaAdLFGgIR0BSaqv3ai9JdX2UKGgGR0BcwAAAAAAAaAdLc2gIR0BScRegL7XQdX2UKGgGR0BAAAAAAAAAaAdLIGgIR0BSc5WzWwu/dX2UKGgGR0BpAAAAAAAAaAdLyGgIR0BSfihrWRRudX2UKGgGR0BfQAAAAAAAaAdLfWgIR0BShWL5ylvZdX2UKGgGR0BBAAAAAAAAaAdLImgIR0BSh6qsEJSjdX2UKGgGR0BGgAAAAAAAaAdLLWgIR0BSi1AiV0LddX2UKGgGR0BhAAAAAAAAaAdLiGgIR0BSkf+jua4MdX2UKGgGR0BDgAAAAAAAaAdLJ2gIR0BSlIZVGTcJdX2UKGgGR0A1AAAAAAAAaAdLFWgIR0BSldMK1G9YdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0BSllWS2Yv4dX2UKGgGR0A2AAAAAAAAaAdLFmgIR0BSmBqbjLjhdX2UKGgGR0A3AAAAAAAAaAdLF2gIR0BSmnBYV6/qdX2UKGgGR0AxAAAAAAAAaAdLEWgIR0BSm6yOaOPvdX2UKGgGR0A2AAAAAAAAaAdLFmgIR0BSnOuaF23bdX2UKGgGR0BuYAAAAAAAaAdL82gIR0BSrlDKHO8kdX2UKGgGR0BkgAAAAAAAaAdLpGgIR0BSvDRhMJyAdX2UKGgGR0BnYAAAAAAAaAdLu2gIR0BSyRMnJDE4dX2UKGgGR0BoQAAAAAAAaAdLwmgIR0BS1Y6XBxgidX2UKGgGR0BbgAAAAAAAaAdLbmgIR0BS3ae5Fw1jdX2UKGgGR0BkAAAAAAAAaAdLoGgIR0BS6EtRNyo5dX2UKGgGR0BiIAAAAAAAaAdLkWgIR0BS8f5YYBNmdX2UKGgGR0BoYAAAAAAAaAdLw2gIR0BTAC/TLGJfdX2UKGgGR0A4AAAAAAAAaAdLGGgIR0BTAZBX0XgtdX2UKGgGR0A2AAAAAAAAaAdLFmgIR0BTAoI8hcJMdX2UKGgGR0BBAAAAAAAAaAdLImgIR0BTBLayrxRVdX2UKGgGR0BjgAAAAAAAaAdLnGgIR0BTDmKIi1RcdX2UKGgGR0BnwAAAAAAAaAdLvmgIR0BTG0y+HrQgdX2UKGgGR0A1AAAAAAAAaAdLFWgIR0BTHKlxffGddX2UKGgGR0BlIAAAAAAAaAdLqWgIR0BTJ4VEd/8VdX2UKGgGR0BuoAAAAAAAaAdL9WgIR0BTOk0rK/21dX2UKGgGR0A2AAAAAAAAaAdLFmgIR0BTPAQtjCpFdX2UKGgGR0A5AAAAAAAAaAdLGWgIR0BTPWgJ1JUYdX2UKGgGR0A+AAAAAAAAaAdLHmgIR0BTPtm16Vt5dX2UKGgGR0BBgAAAAAAAaAdLI2gIR0BTQURradtmdX2UKGgGR0A+AAAAAAAAaAdLHmgIR0BTQ4aLn9vTdX2UKGgGR0BnwAAAAAAAaAdLvmgIR0BTT7JjlPrOdX2UKGgGR0Bw4AAAAAAAaAdNDgFoCEdAU2TWjGkvb3V9lChoBkdAYSAAAAAAAGgHS4loCEdAU20gTyrgfnV9lChoBkdAY0AAAAAAAGgHS5poCEdAU3fsZ5zHTHV9lChoBkdAZCAAAAAAAGgHS6FoCEdAU4bQkX1rZnV9lChoBkdAZgAAAAAAAGgHS7BoCEdAU5LKyOaOP3V9lChoBkdAY+AAAAAAAGgHS59oCEdAU5uk+HJtBXV9lChoBkdAaWAAAAAAAGgHS8toCEdAU6g/Z/Tb4HV9lChoBkdAauAAAAAAAGgHS9doCEdAU7T1oQFs6HV9lChoBkdAagAAAAAAAGgHS9BoCEdAU8HbsWweNnV9lChoBkdAZ8AAAAAAAGgHS75oCEdAU81IiC8OC3V9lChoBkdAcJAAAAAAAGgHTQkBaAhHQFPd0HQhOgx1fZQoaAZHQGygAAAAAABoB0vlaAhHQFPtDKYAsCl1fZQoaAZHQHKwAAAAAABoB00rAWgIR0BUAY0Q9RrKdX2UKGgGR0BqIAAAAAAAaAdL0WgIR0BUDp8KG+K1dX2UKGgGR0BmIAAAAAAAaAdLsWgIR0BUGqU3XI2gdX2UKGgGR0BrYAAAAAAAaAdL22gIR0BUJ/VurIYFdX2UKGgGR0BroAAAAAAAaAdL3WgIR0BUN2Hk92X+dX2UKGgGR0Br4AAAAAAAaAdL32gIR0BURX5aePJadX2UKGgGR0BjYAAAAAAAaAdLm2gIR0BUTwUlAu7IdX2UKGgGR0BkwAAAAAAAaAdLpmgIR0BUXDOcDr7gdX2UKGgGR0Bn4AAAAAAAaAdLv2gIR0BUaaF23azvdX2UKGgGR0BowAAAAAAAaAdLxmgIR0BUdQssg+yJdX2UKGgGR0Bl4AAAAAAAaAdLr2gIR0BUfv4IrvsrdX2UKGgGR0BjoAAAAAAAaAdLnWgIR0BUiN3fQ8fWdX2UKGgGR0BuAAAAAAAAaAdL8GgIR0BUmo0ALiMpdX2UKGgGR0BoQAAAAAAAaAdLwmgIR0BUpqzqrzXjdX2UKGgGR0Bj4AAAAAAAaAdLn2gIR0BUsFBlcyFgdX2UKGgGR0BmoAAAAAAAaAdLtWgIR0BUvX+dbxEwdX2UKGgGR0BpoAAAAAAAaAdLzWgIR0BUyyH6/IsAdX2UKGgGR0BvgAAAAAAAaAdL/GgIR0BU2rbUPQOXdX2UKGgGR0BkwAAAAAAAaAdLpmgIR0BU6Mm4RVZLdX2UKGgGR0BfwAAAAAAAaAdLf2gIR0BU8NwWFev7dX2UKGgGR0BnQAAAAAAAaAdLumgIR0BU/18G9pRGdX2UKGgGR0BiwAAAAAAAaAdLlmgIR0BVCKBy0a60dX2UKGgGR0BnIAAAAAAAaAdLuWgIR0BVFEona37UdX2UKGgGR0BjgAAAAAAAaAdLnGgIR0BVIOM+/xlQdX2UKGgGR0BtIAAAAAAAaAdL6WgIR0BVLyrLhaTwdX2UKGgGR0Bl4AAAAAAAaAdLr2gIR0BVO6vaDf3wdX2UKGgGR0BkgAAAAAAAaAdLpGgIR0BVRy5iExqPdX2UKGgGR0BtYAAAAAAAaAdL62gIR0BVViU1Q66rdX2UKGgGR0BjYAAAAAAAaAdLm2gIR0BVX3uAqd6LdX2UKGgGR0BkAAAAAAAAaAdLoGgIR0BVazLwF1SwdX2UKGgGR0BjAAAAAAAAaAdLmGgIR0BVdLK3d9DydX2UKGgGR0BlYAAAAAAAaAdLq2gIR0BVfxG2CulodX2UKGgGR0BlQAAAAAAAaAdLqmgIR0BViZ4W1twadX2UKGgGR0BzUAAAAAAAaAdNNQFoCEdAVZ+KvV3EAHV9lChoBkdAYIAAAAAAAGgHS4RoCEdAVaaaXrt3OnV9lChoBkdAZiAAAAAAAGgHS7FoCEdAVbJV0cOsk3V9lChoBkdAYYAAAAAAAGgHS4xoCEdAVbqf5DZ13nV9lChoBkdAaGAAAAAAAGgHS8NoCEdAVcgVeruIAXV9lChoBkdAZOAAAAAAAGgHS6doCEdAVdLyz5XU6XV9lChoBkdAeEAAAAAAAGgHTYQBaAhHQFXoqwQlKK51fZQoaAZHQGIAAAAAAABoB0uQaAhHQFXy18stkFx1fZQoaAZHQGQAAAAAAABoB0ugaAhHQFX7pHI6r/91fZQoaAZHQGQAAAAAAABoB0ugaAhHQFYKQokRjBl1fZQoaAZHQGcAAAAAAABoB0u4aAhHQFYVEt/WlM11ZS4="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 12500,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_shape": [
+            4
+        ],
+        "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": "2",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "buffer_size": 1000000,
+    "batch_size": 32,
+    "learning_starts": 50000,
+    "tau": 1.0,
+    "gamma": 0.99,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7fccdbe2b880>",
+        "add": "<function ReplayBuffer.add at 0x7fccdbe2b910>",
+        "sample": "<function ReplayBuffer.sample at 0x7fccdbe2b9a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fccdbe2ba30>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fccdbe2bac0>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fccdbe38600>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "exploration_initial_eps": 1.0,
+    "exploration_final_eps": 0.05,
+    "exploration_fraction": 0.1,
+    "target_update_interval": 10000,
+    "_n_calls": 100000,
+    "max_grad_norm": 10,
+    "exploration_rate": 0.05,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": [],
+    "exploration_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

DQN-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3101cd4bcac94a3e6e0b33145a5d10c6f788dabd3515ed243a339e2877fea6e
+size 545519

DQN-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e939c2da90a7318ad1e094b92cff9e87bf461402005aa126d648493e99deae44
+size 544641

DQN-CartPole-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

DQN-CartPole-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.90.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Jan 27 02:56:13 UTC 2023
+- Python: 3.10.6
+- Stable-Baselines3: 2.1.0
+- PyTorch: 2.0.1+cu117
+- GPU Enabled: False
+- Numpy: 1.25.1
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.26.2

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 189.90 +/- 46.46
+      name: mean_reward
+      verified: false
+---
+
+# **DQN** Agent playing **CartPole-v1**
+This is a trained model of a **DQN** agent playing **CartPole-v1**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -0,0 +1 @@
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=", "__module__": "stable_baselines3.dqn.policies", "__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}", "__doc__": "\n    Policy class with Q-Value Net and target net for DQN\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function DQNPolicy.__init__ at 0x7fccdbe3f1c0>", "_build": "<function DQNPolicy._build at 0x7fccdbe3f250>", "make_q_net": "<function DQNPolicy.make_q_net at 0x7fccdbe3f2e0>", "forward": "<function DQNPolicy.forward at 0x7fccdbe3f370>", "_predict": "<function DQNPolicy._predict at 0x7fccdbe3f400>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7fccdbe3f490>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7fccdbe3f520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fccdbe4e900>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVUQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlChNAAFNAAFldS4=", "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>", "net_arch": [256, 256]}, "num_timesteps": 100000, "_total_timesteps": 100000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1698303731040257432, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAANLDsj1+YN4+BifMPObDCL+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAO7yqD1OZnU+/0z1PKuWgL6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_episode_num": 3751, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 12500, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "buffer_size": 1000000, "batch_size": 32, "learning_starts": 50000, "tau": 1.0, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ", "__init__": "<function ReplayBuffer.__init__ at 0x7fccdbe2b880>", "add": "<function ReplayBuffer.add at 0x7fccdbe2b910>", "sample": "<function ReplayBuffer.sample at 0x7fccdbe2b9a0>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7fccdbe2ba30>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fccdbe2bac0>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fccdbe38600>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "exploration_initial_eps": 1.0, "exploration_final_eps": 0.05, "exploration_fraction": 0.1, "target_update_interval": 10000, "_n_calls": 100000, "max_grad_norm": 10, "exploration_rate": 0.05, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "exploration_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.90.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Jan 27 02:56:13 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cu117", "GPU Enabled": "False", "Numpy": "1.25.1", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 189.9, "std_reward": 46.455247281658075, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-26T12:39:23.964744"}