first try on CP

.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

CartPole-v1-ppo-fastlearner-50k.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe2653bc54a50e152964806b60a02fb61f2735a428aa5d7493c69a866e481ce
+size 134382

CartPole-v1-ppo-fastlearner-50k/_stable_baselines3_version

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

CartPole-v1-ppo-fastlearner-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:": "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",
+        "dtype": "float32",
+        "_shape": [
+            4
+        ],
+        "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 2,
+        "_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": 1652610068.0302222,
+    "learning_rate": 0.0005,
+    "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": -0.3107200000000001,
+    "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
+}

CartPole-v1-ppo-fastlearner-50k/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd924f3b2956a84c0145e592eeb753d5cda86e2f437a6b3dca299fbf9ab2aa11
+size 79709

CartPole-v1-ppo-fastlearner-50k/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403c9325b92d7f423ed22f79f68c7988e0525756eade7e90b2c955b509db6bfe
+size 40641

CartPole-v1-ppo-fastlearner-50k/pytorch_variables.pth

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

CartPole-v1-ppo-fastlearner-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:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 397.00 +/- 103.22
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+---
+
+  # **PPO** Agent playing **CartPole-v1**
+  This is a trained model of a **PPO** agent playing **CartPole-v1** 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:": "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", "dtype": "float32", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 2, "_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": 1652610068.0302222, "learning_rate": 0.0005, "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": -0.3107200000000001, "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 sha256:814aceced5761b1be6c2677f3e73bdd51ddb3395e35c1538b632142636ce2b14
+size 72106

results.json

@@ -0,0 +1 @@
+{"mean_reward": 397.0, "std_reward": 103.22112186950886, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-15T10:23:53.508117"}