PPO colab testing

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: 208.65 +/- 76.60
+      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 0x7c98b8bf7eb0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c98b8bf7f40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c98b8bfc040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c98b8bfc0d0>", "_build": "<function ActorCriticPolicy._build at 0x7c98b8bfc160>", "forward": "<function ActorCriticPolicy.forward at 0x7c98b8bfc1f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c98b8bfc280>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c98b8bfc310>", "_predict": "<function ActorCriticPolicy._predict at 0x7c98b8bfc3a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c98b8bfc430>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c98b8bfc4c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c98b8bfc550>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c98b8d91c80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1702788244233181142, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM0hcb1/gU4/JZflPc8/db4ntXk90ioAvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_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": 3908, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.23.5", "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 sha256:35ce8a7a7ca54423cf9857155461812fa20caa80070d539432913fc5250e131d
+size 147414

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 0x7c98b8bf7eb0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c98b8bf7f40>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c98b8bfc040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c98b8bfc0d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7c98b8bfc160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7c98b8bfc1f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c98b8bfc280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c98b8bfc310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7c98b8bfc3a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c98b8bfc430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c98b8bfc4c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c98b8bfc550>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7c98b8d91c80>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1000448,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1702788244233181142,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM0hcb1/gU4/JZflPc8/db4ntXk90ioAvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.00044800000000000395,
+    "_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": 3908,
+    "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88327ea2bad421722610f178b725b54594b992c0999e58f9a87bc877cc34d7f5
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa7424682f9f7b7a7120a3f3b614dee1b7e4a081904413ceb84aded0adab509
+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: 2.1.0+cu121
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 208.6488859, "std_reward": 76.59831462982929, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-17T05:35:37.194419"}