Upload PPO MountainCar-v0 first run

.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: -200.00 +/- 0.00
+      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 0x7f0b2043a4d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0b2043a560>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0b2043a5f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0b2043a680>", "_build": "<function ActorCriticPolicy._build at 0x7f0b2043a710>", "forward": "<function ActorCriticPolicy.forward at 0x7f0b2043a7a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0b2043a830>", "_predict": "<function ActorCriticPolicy._predict at 0x7f0b2043a8c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0b2043a950>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0b2043a9e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0b2043aa70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f0b20475de0>"}, "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": 32768, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652605768.0146544, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAF3gBr/oZRU8X0/7vkX0Brz+6AW/K1E7uyXwD7/joDg8RAcXv8IbFzucOgS/ab2MuznbCb+l7uc7MVMjv1Y/PzwT6gm/xEIWPEFeFr86uD67nzkWv833IjsbdOa+NSCjOQv+D7/kSZc7OIwdvxde4jtZ7hm/6i8vvO6ECr8Grgk6lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -31.768, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 10, "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": "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"}}

lunar_demo.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad315acc63dbefb8dd9f3ee92bf7b0878ea3f77fce25dc198e1e19e46c312dea
+size 131751

lunar_demo/_stable_baselines3_version

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

lunar_demo/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 0x7f0b2043a4d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0b2043a560>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0b2043a5f0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0b2043a680>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f0b2043a710>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f0b2043a7a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0b2043a830>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f0b2043a8c0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0b2043a950>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0b2043a9e0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0b2043aa70>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f0b20475de0>"
+    },
+    "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": 32768,
+    "_total_timesteps": 1000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1652605768.0146544,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAF3gBr/oZRU8X0/7vkX0Brz+6AW/K1E7uyXwD7/joDg8RAcXv8IbFzucOgS/ab2MuznbCb+l7uc7MVMjv1Y/PzwT6gm/xEIWPEFeFr86uD67nzkWv833IjsbdOa+NSCjOQv+D7/kSZc7OIwdvxde4jtZ7hm/6i8vvO6ECr8Grgk6lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -31.768,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 10,
+    "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
+}

lunar_demo/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac1afa18011b51dafe152e0da883ec4d6e0a6eea34e28c77ded3765a61a1f6c
+size 78173

lunar_demo/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bafa72c490916911c83aff1fef6cd7a2123dd836677ad9062acaac2bb4d4be3a
+size 39873

lunar_demo/pytorch_variables.pth

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

lunar_demo/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:cc02679fe77905e66bf4a118f3852bfb0943bece2e915cb1112bc33e211a91f9
+size 223450

results.json

@@ -0,0 +1 @@
+{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-15T09:11:07.268293"}