Initial Commit

.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 +1,70 @@
+---
+library_name: stable-baselines3
+tags:
+- seals/CartPole-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 500.00 +/- 0.00
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/CartPole-v0
+      type: seals/CartPole-v0
+---
+
+# **PPO** Agent playing **seals/CartPole-v0**
+This is a trained model of a **PPO** agent playing **seals/CartPole-v0**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo ppo --env seals/CartPole-v0 -orga ernestumorga -f logs/
+python enjoy.py --algo ppo --env seals/CartPole-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo ppo --env seals/CartPole-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo ppo --env seals/CartPole-v0 -f logs/ -orga ernestumorga
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('clip_range', 0.4),
+             ('ent_coef', 0.008508727919228772),
+             ('gae_lambda', 0.9),
+             ('gamma', 0.9999),
+             ('learning_rate', 0.0012403278189645594),
+             ('max_grad_norm', 0.8),
+             ('n_envs', 8),
+             ('n_epochs', 10),
+             ('n_steps', 512),
+             ('n_timesteps', 100000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs',
+              'dict(activation_fn=nn.ReLU, net_arch=[dict(pi=[64, 64], vf=[64, '
+              '64])])'),
+             ('vf_coef', 0.489343896591493),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - device
+    - cpu
+  - - env
+    - seals/CartPole-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - seals_experts
+  - - log_interval
+    - -1
+  - - n_eval_envs
+    - 1
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - 4
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3866955406
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - total_n_trials
+    - null
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3

config.yml

@@ -0,0 +1,29 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - clip_range
+    - 0.4
+  - - ent_coef
+    - 0.008508727919228772
+  - - gae_lambda
+    - 0.9
+  - - gamma
+    - 0.9999
+  - - learning_rate
+    - 0.0012403278189645594
+  - - max_grad_norm
+    - 0.8
+  - - n_envs
+    - 8
+  - - n_epochs
+    - 10
+  - - n_steps
+    - 512
+  - - n_timesteps
+    - 100000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(activation_fn=nn.ReLU, net_arch=[dict(pi=[64, 64], vf=[64, 64])])
+  - - vf_coef
+    - 0.489343896591493

env_kwargs.yml

@@ -0,0 +1 @@
+{}

ppo-seals-CartPole-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0430bbef17d9463be60c35cc6cc619a3a6dbc7db81e1d9469b484a1d2c5b156
+size 138640

ppo-seals-CartPole-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.4.1a0

ppo-seals-CartPole-v0/data

@@ -0,0 +1,110 @@
+{
+    "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 0x7fc420aef280>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc420aef310>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc420aef3a0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc420aef430>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fc420aef4c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fc420aef550>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc420aef5e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fc420aef670>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc420aef700>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc420aef790>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc420aef820>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fc420b67870>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVaAAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlH2UKIwCcGmUXZQoS0BLQGWMAnZmlF2UKEtAS0BldWF1Lg==",
+        "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
+        "net_arch": [
+            {
+                "pi": [
+                    64,
+                    64
+                ],
+                "vf": [
+                    64,
+                    64
+                ]
+            }
+        ]
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            4
+        ],
+        "low": "[-3.4028235e+38 -3.4028235e+38 -3.1415927e+00 -3.4028235e+38]",
+        "high": "[3.4028235e+38 3.4028235e+38 3.1415927e+00 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:": "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",
+        "n": 2,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 8,
+    "num_timesteps": 102400,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1651240811.8226469,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.02400000000000002,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 250,
+    "n_steps": 512,
+    "gamma": 0.9999,
+    "gae_lambda": 0.9,
+    "ent_coef": 0.008508727919228772,
+    "vf_coef": 0.489343896591493,
+    "max_grad_norm": 0.8,
+    "batch_size": 256,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVmAIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjGgvbmFzL3VjYi9tYXhpbWlsaWFuL3JsLWJhc2VsaW5lczMtem9vL3ZlbnYvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5RoDXVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/ZmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "clip_range_vf": null,
+    "target_kl": null,
+    "normalize_advantage": true
+}

ppo-seals-CartPole-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d017cd4add2514e12384da546ec6ed5303da8dd59711d3d8fc5c2b28a4575c3
+size 79453

ppo-seals-CartPole-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b7f8bd78b461cde84c74f83d80b296a12c5a9206435029ce843acec812a023f
+size 40513

ppo-seals-CartPole-v0/pytorch_variables.pth

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

ppo-seals-CartPole-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.0-109-generic-x86_64-with-glibc2.29 #123-Ubuntu SMP Fri Apr 8 09:10:54 UTC 2022
+Python: 3.8.10
+Stable-Baselines3: 1.4.1a0
+PyTorch: 1.11.0+cu102
+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 sha256:1c1428837404497e463bb6328186283ec09068bce8601f5d59ca3f46bbde225b
+size 55885

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-28T14:06:50.696510"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e9479340a3b7324125e6ab6b6e913dcd48421d53b468708ab3fbcf8c814931
+size 6634