Upload PPO MountainCar-v0 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:
+- MountainCar-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -127.50 +/- 20.23
+      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 0x7f96abc977a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f96abc97830>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f96abc978c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f96abc97950>", "_build": "<function ActorCriticPolicy._build at 0x7f96abc979e0>", "forward": "<function ActorCriticPolicy.forward at 0x7f96abc97a70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f96abc97b00>", "_predict": "<function ActorCriticPolicy._predict at 0x7f96abc97b90>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f96abc97c20>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f96abc97cb0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f96abc97d40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f96abcdbc30>"}, "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": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652362559.7079582, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAABYZGb89BkM8aXgqvTbh/bzCRzC/vEoGvVWRAr9ZPoe8SwO+vrlv8Dw/uvq+rMVhvIs9h76deAA9Rc9Nvx496LxbqxC+it8wPWTcIb+ZZ6284dz8vtapmTxOahq/6ucuvGlwMb/mSwW92PPcvkgSZLzV3Be/FZu4u9Pmj78ir5w8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="}, "_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": 2048, "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": 8, "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": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-MountainCar-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a6139a0584585287df7a40c46669f34cfb082918e013f020435d14e26e29266
+size 131836

ppo-MountainCar-v0/_stable_baselines3_version

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

ppo-MountainCar-v0/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 0x7f96abc977a0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f96abc97830>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f96abc978c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f96abc97950>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f96abc979e0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f96abc97a70>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f96abc97b00>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f96abc97b90>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f96abc97c20>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f96abc97cb0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f96abc97d40>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f96abcdbc30>"
+    },
+    "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": 16,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1652362559.7079582,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAABYZGb89BkM8aXgqvTbh/bzCRzC/vEoGvVWRAr9ZPoe8SwO+vrlv8Dw/uvq+rMVhvIs9h76deAA9Rc9Nvx496LxbqxC+it8wPWTcIb+ZZ6284dz8vtapmTxOahq/6ucuvGlwMb/mSwW92PPcvkgSZLzV3Be/FZu4u9Pmj78ir5w8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+    },
+    "_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": 2048,
+    "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": 8,
+    "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:db5a585bff41ec002411aa7292b582b94373ad9e705df0a73d8c4f2ee740707c
+size 78237

ppo-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bbb4d159399976cb018f74d1ad973de022665efb6d8e74dfc15c24218915dc0
+size 39873

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: 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:ee801debe13a89aedffca65780bc9482c0f3c472268421f607f57eb0be019151
+size 257661

results.json

@@ -0,0 +1 @@
+{"mean_reward": -127.5, "std_reward": 20.22992832414391, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T13:55:02.754538"}