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:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -773.89 +/- 610.64
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+---
+
+  # **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
+  

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 0x7fb199a5e700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb199a5e790>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb199a5e820>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb199a5e8b0>", "_build": "<function ActorCriticPolicy._build at 0x7fb199a5e940>", "forward": "<function ActorCriticPolicy.forward at 0x7fb199a5e9d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb199a5ea60>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb199a5eaf0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb199a5eb80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb199a5ec10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb199a5eca0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fb199a5f740>"}, "verbose": 0, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_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": 1, "num_timesteps": 5120, "_total_timesteps": 5000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652289003.7817495, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGba0LwAIKM/kjJmvkM5Fb+Xz1s9Ky90PQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 20, "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": 1024, "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-5.13.0-40-generic-x86_64-with-glibc2.31 #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148d46a353fbc1963897073109c700ebb8bdf99234fd2410486e8b96c2acde10
+size 141082

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-LunarLander-v2/data

@@ -0,0 +1,94 @@
+{
+    "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 0x7fb199a5e700>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb199a5e790>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb199a5e820>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb199a5e8b0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fb199a5e940>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fb199a5e9d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb199a5ea60>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fb199a5eaf0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb199a5eb80>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb199a5ec10>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb199a5eca0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fb199a5f740>"
+    },
+    "verbose": 0,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            8
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_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": 1,
+    "num_timesteps": 5120,
+    "_total_timesteps": 5000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1652289003.7817495,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGba0LwAIKM/kjJmvkM5Fb+Xz1s9Ky90PQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.02400000000000002,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 20,
+    "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": 1024,
+    "n_epochs": 4,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee1c0b5c636a744190de5ea8f1b3f0f9ba6edcc83c1d58dda82c8c104189562
+size 84829

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39407312110448fdc83190d9693ab510ccbb12a77757deb4ac7a1983d43ab079
+size 43201

ppo-LunarLander-v2/pytorch_variables.pth

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

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.13.0-40-generic-x86_64-with-glibc2.31 #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022
+Python: 3.9.12
+Stable-Baselines3: 1.5.0
+PyTorch: 1.11.0+cu102
+GPU Enabled: True
+Numpy: 1.22.3
+Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": -773.8854753263179, "std_reward": 610.635574137478, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T20:15:39.594929"}