initial commit of RL course

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: MlpPolicy
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 232.07 +/- 12.43
+      name: mean_reward
+      verified: false
+---
+
+# **MlpPolicy** Agent playing **LunarLander-v2**
+This is a trained model of a **MlpPolicy** agent playing **LunarLander-v2**
+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:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ActorCriticPolicy.__init__ at 0x7af2aee4acb0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7af2aee4ad40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7af2aee4add0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7af2aee4ae60>", "_build": "<function ActorCriticPolicy._build at 0x7af2aee4aef0>", "forward": "<function ActorCriticPolicy.forward at 0x7af2aee4af80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7af2aee4b010>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7af2aee4b0a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7af2aee4b130>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7af2aee4b1c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7af2aee4b250>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7af2aee4b2e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7af2aee30540>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1726101156129267350, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_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": 310, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5a729b8cceb3637fcb7d92f8bd45e064978dc47897e6383efb2e0e9b37ce27c
+size 148087

ppo-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

ppo-LunarLander-v2/data

@@ -0,0 +1,99 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__module__": "stable_baselines3.common.policies",
+        "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ActorCriticPolicy.__init__ at 0x7af2aee4acb0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7af2aee4ad40>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7af2aee4add0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7af2aee4ae60>",
+        "_build": "<function ActorCriticPolicy._build at 0x7af2aee4aef0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7af2aee4af80>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7af2aee4b010>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7af2aee4b0a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7af2aee4b130>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7af2aee4b1c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7af2aee4b250>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7af2aee4b2e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7af2aee30540>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1726101156129267350,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.015808000000000044,
+    "_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": 310,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd2045b41c2c10a5c4a3efe1a95347652d3c4fe5f3c029f02193db14e68ae1c
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8df6c3bc960bc4d222a44f4807aeccce9f79606e4c50e1726ddd5a9c1c1899b
+size 43762

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.4.0+cu121
+- GPU Enabled: True
+- Numpy: 1.26.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 232.0664165, "std_reward": 12.434654900552845, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-12T01:31:46.181119"}