1M training steps

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,28 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 500.00 +/- 0.00
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+---
+
+  # **PPO** Agent playing **CartPole-v1**
+  This is a trained model of a **PPO** agent playing **CartPole-v1** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+  
+  ## Usage (with Stable-baselines3)
+  TODO: Add your code
+  

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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7fdd1d78def0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fdd1d78df80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fdd1d796050>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fdd1d7960e0>", "_build": "<function ActorCriticPolicy._build at 0x7fdd1d796170>", "forward": "<function ActorCriticPolicy.forward at 0x7fdd1d796200>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fdd1d796290>", "_predict": "<function ActorCriticPolicy._predict at 0x7fdd1d796320>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fdd1d7963b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fdd1d796440>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fdd1d7964d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fdd1d7e19c0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 2, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652985499.1165571, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08595b700c4edf8cc9f9b8f679f193ee286cb71f2b8c3f3150d7ad28f60475bc
+size 133939

ppo-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.0

ppo-CartPole-v1/data

@@ -0,0 +1,91 @@
+{
+    "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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7fdd1d78def0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fdd1d78df80>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fdd1d796050>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fdd1d7960e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fdd1d796170>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fdd1d796200>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fdd1d796290>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fdd1d796320>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fdd1d7963b0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fdd1d796440>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fdd1d7964d0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fdd1d7e19c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            4
+        ],
+        "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 2,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1652985499.1165571,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_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,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 248,
+    "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
+}

ppo-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95bd79057e29d4a6b26227bb24dfbc9ddef101845e08f8158dc556855f3905bb
+size 79709

ppo-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72e16d9d8164c8c372bf8dd1b67b744e9cddc9d17d0c9582fdc3c4586e8c19f
+size 40641

ppo-CartPole-v1/pytorch_variables.pth

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

ppo-CartPole-v1/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
+Python: 3.7.13
+Stable-Baselines3: 1.5.0
+PyTorch: 1.11.0+cu113
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0829a62d4b495da1ee678e321972510013566c71b970b6dc32e30e10b7bf5c
+size 60877

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-19T18:50:54.044046"}