first try on MC

.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

MountainCar-v0-ppo-50k.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d095c1e247a44570596ef8c96986d34d312a435ace700442c76001cec294a6ac
+size 131764

MountainCar-v0-ppo-50k/_stable_baselines3_version

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

MountainCar-v0-ppo-50k/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 0x7f956e0d3320>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f956e0d33b0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f956e0d3440>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f956e0d34d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f956e0d3560>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f956e0d35f0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f956e0d3680>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f956e0d3710>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f956e0d37a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f956e0d3830>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f956e0d38c0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f956e11e6c0>"
+    },
+    "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": 65536,
+    "_total_timesteps": 50000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1652611593.3756137,
+    "learning_rate": 0.0005,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAIF++b674AM7/9ULv4Lnv7sTPQm/6JKTu786/r6dICK8+/QRv6bRb7kgkwu/M4kPvC4MDL8Zlow6iPUZv+UpA7ybYte+ukuEupJ4/L7GrzE7Mr4Dv+OXOLwpRBK/QCj6u8XeBb+V0Xg5Mg8ev3G7UbxhYCO/iz8DvESgE7+qJDy8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.3107200000000001,
+    "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": 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
+}

MountainCar-v0-ppo-50k/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:defe65766158962d4a6d11ae427bd380686ab830a2ef8c2adcfcac74440dde86
+size 78173

MountainCar-v0-ppo-50k/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c337cbb6adbb043b64d14dc7ce425c82e0262a759b713be92d972f70dbb8b5e8
+size 39873

MountainCar-v0-ppo-50k/pytorch_variables.pth

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

MountainCar-v0-ppo-50k/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

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 0x7f956e0d3320>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f956e0d33b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f956e0d3440>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f956e0d34d0>", "_build": "<function ActorCriticPolicy._build at 0x7f956e0d3560>", "forward": "<function ActorCriticPolicy.forward at 0x7f956e0d35f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f956e0d3680>", "_predict": "<function ActorCriticPolicy._predict at 0x7f956e0d3710>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f956e0d37a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f956e0d3830>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f956e0d38c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f956e11e6c0>"}, "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": 65536, "_total_timesteps": 50000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652611593.3756137, "learning_rate": 0.0005, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAIF++b674AM7/9ULv4Lnv7sTPQm/6JKTu786/r6dICK8+/QRv6bRb7kgkwu/M4kPvC4MDL8Zlow6iPUZv+UpA7ybYte+ukuEupJ4/L7GrzE7Mr4Dv+OXOLwpRBK/QCj6u8XeBb+V0Xg5Mg8ev3G7UbxhYCO/iz8DvESgE7+qJDy8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.3107200000000001, "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": 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"}}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb11fc004d7d76a99fa9b17870b70ebe8016542fe65d0657089c8b1cb48ab4b0
+size 231671

results.json

@@ -0,0 +1 @@
+{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-15T10:48:10.890218"}