Upload PPO LunarLander-v2 trained agent

.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:
+- FrozenLake-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 0.70 +/- 0.46
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: FrozenLake-v1
+      type: FrozenLake-v1
+---
+
+  # **PPO** Agent playing **FrozenLake-v1**
+  This is a trained model of a **PPO** agent playing **FrozenLake-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 0x7fcc9a9daa70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcc9a9dab00>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcc9a9dab90>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcc9a9dac20>", "_build": "<function ActorCriticPolicy._build at 0x7fcc9a9dacb0>", "forward": "<function ActorCriticPolicy.forward at 0x7fcc9a9dad40>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcc9a9dadd0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fcc9a9dae60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcc9a9daef0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcc9a9daf80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcc9a9e1050>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fcc9aa1cd20>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLEIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 16, "_shape": [], "dtype": "int64", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1212416, "_total_timesteps": 1200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652745639.4016604, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAQAAAAAAAAADgAAAAAAAAAKAAAAAAAAAAkAAAAAAAAABAAAAAAAAAAEAAAAAAAAAAkAAAAAAAAACAAAAAAAAAAIAAAAAAAAAAAAAAAAAAAACAAAAAAAAAAJAAAAAAAAAAkAAAAAAAAACAAAAAAAAAAIAAAAAAAAAAQAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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": -0.010346666666666726, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 496, "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-FrozenLake-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e272d16c9fc3eb29473a566286262a1305a4d5f48f0113adc74f0ebdcc596e42
+size 153659

ppo-FrozenLake-v1/_stable_baselines3_version

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

ppo-FrozenLake-v1/data

@@ -0,0 +1,89 @@
+{
+    "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 0x7fcc9a9daa70>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcc9a9dab00>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcc9a9dab90>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcc9a9dac20>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fcc9a9dacb0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fcc9a9dad40>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcc9a9dadd0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fcc9a9dae60>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcc9a9daef0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcc9a9daf80>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcc9a9e1050>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fcc9aa1cd20>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLEIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 16,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 1212416,
+    "_total_timesteps": 1200000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1652745639.4016604,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAQAAAAAAAAADgAAAAAAAAAKAAAAAAAAAAkAAAAAAAAABAAAAAAAAAAEAAAAAAAAAAkAAAAAAAAACAAAAAAAAAAIAAAAAAAAAAAAAAAAAAAACAAAAAAAAAAJAAAAAAAAAAkAAAAAAAAACAAAAAAAAAAIAAAAAAAAAAQAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
+    },
+    "_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": -0.010346666666666726,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 496,
+    "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-FrozenLake-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3871de714ee42af0fd9e8a9d79aed4024e091a2991472cbff3f7a80250da7ac7
+size 93085

ppo-FrozenLake-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e75ed8ff390beea9722e28f7e90895fca306a29477c6de00f19ac6e8381af3
+size 47297

ppo-FrozenLake-v1/pytorch_variables.pth

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

ppo-FrozenLake-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

results.json

@@ -0,0 +1 @@
+{"mean_reward": 0.7, "std_reward": 0.45825756949558394, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-17T00:15:48.386023"}