Finished model of unit 1

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: 200.88 +/- 51.81
+      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 0x7a54e8937ac0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a54e8937b50>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a54e8937be0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a54e8937c70>", "_build": "<function ActorCriticPolicy._build at 0x7a54e8937d00>", "forward": "<function ActorCriticPolicy.forward at 0x7a54e8937d90>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a54e8937e20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a54e8937eb0>", "_predict": "<function ActorCriticPolicy._predict at 0x7a54e8937f40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a54e8744040>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a54e87440d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a54e8744160>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a54e88c8440>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 131072, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1724928461096908718, "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": -0.3107200000000001, "_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": 121, "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": 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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"}, "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 sha256:2bc227092a5e4412a1d39f47d862dfe39bbce6065e23d4a4ab20457f5abed31d
+size 147324

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 0x7a54e8937ac0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a54e8937b50>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a54e8937be0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a54e8937c70>",
+        "_build": "<function ActorCriticPolicy._build at 0x7a54e8937d00>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7a54e8937d90>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a54e8937e20>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a54e8937eb0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7a54e8937f40>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a54e8744040>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a54e87440d0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a54e8744160>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7a54e88c8440>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 131072,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1724928461096908718,
+    "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": -0.3107200000000001,
+    "_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": 121,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
+        "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": 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:f4a46d0d763308e67bcc72b74b3699d78c39f0a0d90c7580185dbc556d8a8129
+size 88490

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f9bed5d81a0dbd0e656ced56ecc9eb1043f32a32ac6f388e1949deec7ee371
+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": 200.87754890000002, "std_reward": 51.811416181167885, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-29T11:04:35.230217"}