Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst 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 +1,82 @@
+---
+library_name: stable-baselines3
+tags:
+- seals/CartPole-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/CartPole-v0
+      type: seals/CartPole-v0
+    metrics:
+    - type: mean_reward
+      value: 500.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **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
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo ppo --env seals/CartPole-v0 -orga ernestum -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env seals/CartPole-v0  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo ppo --env seals/CartPole-v0 -orga ernestum -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env seals/CartPole-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env seals/CartPole-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env seals/CartPole-v0 -f logs/ -orga ernestum
+```
+
+## 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',
+              {'activation_fn': <class 'torch.nn.modules.activation.ReLU'>,
+               'net_arch': [{'pi': [64, 64], 'vf': [64, 64]}]}),
+             ('vf_coef', 0.489343896591493),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - conf_file
+    - hyperparams/python/ppo.py
+  - - device
+    - cpu
+  - - env
+    - seals/CartPole-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 0
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - - seals
+  - - hyperparams
+    - null
+  - - log_folder
+    - gymnasium_models
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - 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
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 705888933
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,36 @@
+!!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
+    - activation_fn: !!python/name:torch.nn.modules.activation.ReLU ''
+      net_arch:
+      - 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 sha256:6289bb697fc0f1e7637e587652d2d776145618358af91920d8992712a943879a
+size 139001

ppo-seals-CartPole-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+2.1.0

ppo-seals-CartPole-v0/data

@@ -0,0 +1,113 @@
+{
+    "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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7fc203108040>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc2031080d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc203108160>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc2031081f0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fc203108280>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fc203108310>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc2031083a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc203108430>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fc2031084c0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc203108550>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc2031085e0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc203108670>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fc2030e5a80>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVZQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJR9lCiMAnBplF2UKEtAS0BljAJ2ZpRdlChLQEtAZXV1Lg==",
+        "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
+        "net_arch": {
+            "pi": [
+                64,
+                64
+            ],
+            "vf": [
+                64,
+                64
+            ]
+        }
+    },
+    "num_timesteps": 102400,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1694771152136710495,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_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,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 250,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_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]",
+        "low_repr": "[-3.4028235e+38 -3.4028235e+38 -3.1415927e+00 -3.4028235e+38]",
+        "high_repr": "[3.4028235e+38 3.4028235e+38 3.1415927e+00 3.4028235e+38]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": "2",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "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:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVlwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZS9ob21lL21heGltaWxpYW4vcmwtYmFzZWxpbmVzMy16b28vdmVudi9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLg0MCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgMdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHn2UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP1RST9rNKDOFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    }
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40da409386ebbb12b110342c54781f79f6bb75a7011b5c77349fc23803476222
+size 82425

ppo-seals-CartPole-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db5d09a0139e686bcea8d28033d45282a219872cdf9615bd34f323321953549
+size 40641

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 +1,9 @@
+- OS: Linux-5.4.0-156-generic-x86_64-with-glibc2.29 # 173-Ubuntu SMP Tue Jul 11 07:25:22 UTC 2023
+- Python: 3.8.10
+- Stable-Baselines3: 2.1.0
+- PyTorch: 2.0.1+cu117
+- GPU Enabled: False
+- Numpy: 1.24.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-15T13:56:17.720409"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761f4110060ae02a1ee41e137ab087b607b678b3485f113639424090116ef535
+size 6345