Upload PPO LunarLander-v2 trained agent

PPO-relu-2M.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c196dcef13f9550066f59d7a638898b0f819f4e9166a6f80010143a612fe2cc
+size 145398

PPO-relu-2M/_stable_baselines3_version

@@ -0,0 +1 @@
+2.2.1

PPO-relu-2M/data

@@ -0,0 +1,111 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVIwAAAAAAAACMCWFsZ29yaXRobZSMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__module__": "algorithm",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fca1428e320>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fca1428e3b0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fca1428e440>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fca1428e4d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fca1428e560>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fca1428e5f0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fca1428e680>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fca1428e710>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fca1428e7a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fca1428e830>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fca1428e8c0>",
+        "__doc__": null,
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fca14295dc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 2015232,
+    "_total_timesteps": 2000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1700966632732650000,
+    "learning_rate": 0.0003,
+    "tensorboard_log": "./tensorboard",
+    "_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": -0.007616000000000067,
+    "_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": 492,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "gAWVZgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAADAvwAAwL8AAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAwD8AAMA/AACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFNbLTEuNSAgICAgICAtMS41ICAgICAgIC01LiAgICAgICAgLTUuICAgICAgICAtMy4xNDE1OTI3IC01LgogLTAuICAgICAgICAtMC4gICAgICAgXZSMCWhpZ2hfcmVwcpSMS1sxLjUgICAgICAgMS41ICAgICAgIDUuICAgICAgICA1LiAgICAgICAgMy4xNDE1OTI3IDUuICAgICAgICAxLgogMS4gICAgICAgXZSMCl9ucF9yYW5kb22UTnViLg==",
+        "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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]",
+        "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]",
+        "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]",
+        "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 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,
+    "rollout_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=",
+        "__module__": "stable_baselines3.common.buffers",
+        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
+        "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\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 gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7fca13d55990>",
+        "reset": "<function RolloutBuffer.reset at 0x7fca13d55a20>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fca13d55ab0>",
+        "add": "<function RolloutBuffer.add at 0x7fca13d55b40>",
+        "get": "<function RolloutBuffer.get at 0x7fca13d55bd0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7fca13d55c60>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fca13d52740>"
+    },
+    "rollout_buffer_kwargs": {},
+    "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-relu-2M/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd724eed7811548acca33549ab6b879353b4ea8ea5c716da083ce7deecb20f3b
+size 87545

PPO-relu-2M/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed16d73af4dc2cacbc0de4a11763bf95f5e0e51d913c058d32882e0f987a96a2
+size 42945

PPO-relu-2M/pytorch_variables.pth

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

PPO-relu-2M/system_info.txt

@@ -0,0 +1,8 @@
+- OS: macOS-10.16-x86_64-i386-64bit Darwin Kernel Version 21.5.0: Tue Apr 26 21:08:37 PDT 2022; root:xnu-8020.121.3~4/RELEASE_ARM64_T6000
+- Python: 3.10.13
+- Stable-Baselines3: 2.2.1
+- PyTorch: 1.13.1
+- GPU Enabled: False
+- Numpy: 1.26.2
+- Cloudpickle: 3.0.0
+- Gymnasium: 0.29.1

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: 275.80 +/- 18.54
+      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:": "gAWVIwAAAAAAAACMCWFsZ29yaXRobZSMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "algorithm", "__init__": "<function ActorCriticPolicy.__init__ at 0x7fca1428e320>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fca1428e3b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fca1428e440>", "_build": "<function ActorCriticPolicy._build at 0x7fca1428e4d0>", "forward": "<function ActorCriticPolicy.forward at 0x7fca1428e560>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fca1428e5f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fca1428e680>", "_predict": "<function ActorCriticPolicy._predict at 0x7fca1428e710>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fca1428e7a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fca1428e830>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fca1428e8c0>", "__doc__": null, "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fca14295dc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1700966632732650000, "learning_rate": 0.0003, "tensorboard_log": "./tensorboard", "_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": -0.007616000000000067, "_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": 492, "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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 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, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\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 gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x7fca13d55990>", "reset": "<function RolloutBuffer.reset at 0x7fca13d55a20>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fca13d55ab0>", "add": "<function RolloutBuffer.add at 0x7fca13d55b40>", "get": "<function RolloutBuffer.get at 0x7fca13d55bd0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7fca13d55c60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fca13d52740>"}, "rollout_buffer_kwargs": {}, "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": "macOS-10.16-x86_64-i386-64bit Darwin Kernel Version 21.5.0: Tue Apr 26 21:08:37 PDT 2022; root:xnu-8020.121.3~4/RELEASE_ARM64_T6000", "Python": "3.10.13", "Stable-Baselines3": "2.2.1", "PyTorch": "1.13.1", "GPU Enabled": "False", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 275.79995169999995, "std_reward": 18.535276891476446, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-25T22:03:10.083752"}