Upload PPO Mountain trained model

.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:
+- MountainCar-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -97.20 +/- 7.12
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCar-v0
+      type: MountainCar-v0
+---
+
+  # **PPO** Agent playing **MountainCar-v0**
+  This is a trained model of a **PPO** agent playing **MountainCar-v0** 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 0x138119c10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x138119ca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x138119d30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x138119dc0>", "_build": "<function ActorCriticPolicy._build at 0x138119e50>", "forward": "<function ActorCriticPolicy.forward at 0x138119ee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x138119f70>", "_predict": "<function ActorCriticPolicy._predict at 0x138120040>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1381200d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x138120160>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x1381201f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x12fec56c0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "dtype": "float32", "_shape": [2], "low": "[-1.2  -0.07]", "high": "[0.6  0.07]", "bounded_below": "[ True  True]", "bounded_above": "[ True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 3, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 1000000, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651836900.860854, "learning_rate": 0.0003, "tensorboard_log": "logs", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_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": 0.6668586666666667, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 9770, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "macOS-12.3.1-arm64-arm-64bit Darwin Kernel Version 21.4.0: Fri Mar 18 00:46:32 PDT 2022; root:xnu-8020.101.4~15/RELEASE_ARM64_T6000", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0", "GPU Enabled": "False", "Numpy": "1.22.3", "Gym": "0.21.0"}}

ppo-mountaincar-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568ecec89897b61ced38c6a42afbff1b1ae41a174c965ba5eb0efe445b5d8fc0
+size 131199

ppo-mountaincar-v0/_stable_baselines3_version

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

ppo-mountaincar-v0/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 0x138119c10>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x138119ca0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x138119d30>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x138119dc0>",
+        "_build": "<function ActorCriticPolicy._build at 0x138119e50>",
+        "forward": "<function ActorCriticPolicy.forward at 0x138119ee0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x138119f70>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x138120040>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1381200d0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x138120160>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x1381201f0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x12fec56c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 3,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 3000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1651836900.860854,
+    "learning_rate": 0.0003,
+    "tensorboard_log": "logs",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_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": 0.6668586666666667,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 9770,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-mountaincar-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45693dd5d0443ac23fb575222c43407d4f9a50538620a4d4bc77f98cc5887735
+size 77981

ppo-mountaincar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1846b1e796086b58e19bcfaeb84929f3876a79a9d306b4603d3df964e5b5bc2
+size 39745

ppo-mountaincar-v0/pytorch_variables.pth

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

ppo-mountaincar-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: macOS-12.3.1-arm64-arm-64bit Darwin Kernel Version 21.4.0: Fri Mar 18 00:46:32 PDT 2022; root:xnu-8020.101.4~15/RELEASE_ARM64_T6000
+Python: 3.9.12
+Stable-Baselines3: 1.5.0
+PyTorch: 1.11.0
+GPU Enabled: False
+Numpy: 1.22.3
+Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e55d12c57b547e49fec877ac112d39a27c14e117bb4c337b55717e1afbc54a
+size 477576

results.json

@@ -0,0 +1 @@
+{"mean_reward": -97.2, "std_reward": 7.124605252222751, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T20:11:15.040017"}