First train of PPO on LunarLander for Unit 1 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: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 262.29 +/- 23.03
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** 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 0x7a3bdd911b40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a3bdd911bd0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a3bdd911c60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a3bdd911cf0>", "_build": "<function ActorCriticPolicy._build at 0x7a3bdd911d80>", "forward": "<function ActorCriticPolicy.forward at 0x7a3bdd911e10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a3bdd911ea0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a3bdd911f30>", "_predict": "<function ActorCriticPolicy._predict at 0x7a3bdd911fc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a3bdd912050>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a3bdd9120e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a3bdd912170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a3bde21f140>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1714136172854356346, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_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": 248, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "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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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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 sha256:75ff7e96f7766aebc6e6561a6b190915b6e9de79fd5676dbf434481354062712
+size 147326

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-LunarLander-v2/data

@@ -0,0 +1,96 @@
+{
+    "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 0x7a3bdd911b40>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a3bdd911bd0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a3bdd911c60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a3bdd911cf0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7a3bdd911d80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7a3bdd911e10>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a3bdd911ea0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a3bdd911f30>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7a3bdd911fc0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a3bdd912050>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a3bdd9120e0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a3bdd912170>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7a3bde21f140>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000.0,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1714136172854356346,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_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": 248,
+    "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 1,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 4,
+    "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:a0883fe29e221b7cb3c785548b64f42739c7460296b37079fd2718c9d93f40ff
+size 88490

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a14a1d32d04a5e272ca77e73da8a0621f805ba15d7d1f38974237b0d54f341ec
+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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.2.1+cu121
+- GPU Enabled: True
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 262.2896671, "std_reward": 23.030810657635513, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-26T13:41:32.988708"}