feat: Add first version of RL PPO for LunarLanderV2

README.md

@@ -1,3 +1,36 @@
 ---
-license: apache-2.0
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 271.94 +/- 21.72
+      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
+
+
+```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 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 0x7fa42494a440>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa42494a4d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa42494a560>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa42494a5f0>", "_build": "<function ActorCriticPolicy._build at 0x7fa42494a680>", "forward": "<function ActorCriticPolicy.forward at 0x7fa42494a710>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa42494a7a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa42494a830>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa42494a8c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa42494a950>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa42494a9e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fa424999720>"}, "verbose": 1, "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1638400, "_total_timesteps": 1628494, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1658929716.8441234, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_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": -0.006082920784479473, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 500, "n_steps": 1024, "gamma": 0.9946247470950147, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 5, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "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": "1.6.0", "PyTorch": "1.12.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d8fc2cbef60848dfd9980556af2175b02b54d15df4db273c238e82f4db452a
+size 147183

ppo-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.0

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 0x7fa42494a440>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa42494a4d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa42494a560>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa42494a5f0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fa42494a680>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fa42494a710>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa42494a7a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fa42494a830>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa42494a8c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa42494a950>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa42494a9e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fa424999720>"
+    },
+    "verbose": 1,
+    "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 1638400,
+    "_total_timesteps": 1628494,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1658929716.8441234,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_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": -0.006082920784479473,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 500,
+    "n_steps": 1024,
+    "gamma": 0.9946247470950147,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 5,
+    "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:db27f323f62958cc78aea63b95308eb6cad2d8134b693e1ad61cc6152681e718
+size 87993

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c164637d6ea4f951164ddb294a31c4e8e8e4b653f9b7e26084cf17170f2509
+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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
+Python: 3.7.13
+Stable-Baselines3: 1.6.0
+PyTorch: 1.12.0+cu113
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": 271.9413392431372, "std_reward": 21.72017018643554, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-28T09:40:53.143086"}