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 +1,88 @@
+---
+library_name: stable-baselines3
+tags:
+- seals/Ant-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/Ant-v1
+      type: seals/Ant-v1
+    metrics:
+    - type: mean_reward
+      value: 2461.22 +/- 674.80
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **seals/Ant-v1**
+This is a trained model of a **PPO** agent playing **seals/Ant-v1**
+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/Ant-v1 -orga ernestum -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env seals/Ant-v1  -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/Ant-v1 -orga ernestum -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env seals/Ant-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env seals/Ant-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env seals/Ant-v1 -f logs/ -orga ernestum
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 16),
+             ('clip_range', 0.3),
+             ('ent_coef', 3.1441389214159857e-06),
+             ('gae_lambda', 0.8),
+             ('gamma', 0.995),
+             ('learning_rate', 0.00017959211641976886),
+             ('max_grad_norm', 0.9),
+             ('n_epochs', 10),
+             ('n_steps', 2048),
+             ('n_timesteps', 1000000.0),
+             ('normalize',
+              {'gamma': 0.995, 'norm_obs': False, 'norm_reward': True}),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs',
+              {'activation_fn': <class 'torch.nn.modules.activation.Tanh'>,
+               'features_extractor_class': <class 'imitation.policies.base.NormalizeFeaturesExtractor'>,
+               'net_arch': [{'pi': [64, 64], 'vf': [64, 64]}]}),
+             ('vf_coef', 0.4351450387648799),
+             ('normalize_kwargs',
+              {'norm_obs': {'gamma': 0.995,
+                            'norm_obs': False,
+                            'norm_reward': True},
+               'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - conf_file
+    - hyperparams/python/ppo.py
+  - - device
+    - cpu
+  - - env
+    - seals/Ant-v1
+  - - 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
+    - 540179516
+  - - 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 +1,39 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 16
+  - - clip_range
+    - 0.3
+  - - ent_coef
+    - 3.1441389214159857e-06
+  - - gae_lambda
+    - 0.8
+  - - gamma
+    - 0.995
+  - - learning_rate
+    - 0.00017959211641976886
+  - - max_grad_norm
+    - 0.9
+  - - n_epochs
+    - 10
+  - - n_steps
+    - 2048
+  - - n_timesteps
+    - 1000000.0
+  - - normalize
+    - gamma: 0.995
+      norm_obs: false
+      norm_reward: true
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - activation_fn: !!python/name:torch.nn.modules.activation.Tanh ''
+      features_extractor_class: !!python/name:imitation.policies.base.NormalizeFeaturesExtractor ''
+      net_arch:
+      - pi:
+        - 64
+        - 64
+        vf:
+        - 64
+        - 64
+  - - vf_coef
+    - 0.4351450387648799

env_kwargs.yml

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

ppo-seals-Ant-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb7c256d659b65c4403f9f9a0301ce555d5c120262cae79b8b0399f51d4b8b0
+size 187043

ppo-seals-Ant-v1/_stable_baselines3_version

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

ppo-seals-Ant-v1/data

@@ -0,0 +1,123 @@
+{
+    "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 0x7f2f1d27d040>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2f1d27d0d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2f1d27d160>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2f1d27d1f0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f2f1d27d280>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f2f1d27d310>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f2f1d27d3a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2f1d27d430>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f2f1d27d4c0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2f1d27d550>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2f1d27d5e0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2f1d27d670>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f2f1d259bd0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVuQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJR9lCiMAnBplF2UKEtAS0BljAJ2ZpRdlChLQEtAZXWMGGZlYXR1cmVzX2V4dHJhY3Rvcl9jbGFzc5SMF2ltaXRhdGlvbi5wb2xpY2llcy5iYXNllIwaTm9ybWFsaXplRmVhdHVyZXNFeHRyYWN0b3KUk5R1Lg==",
+        "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>",
+        "net_arch": {
+            "pi": [
+                64,
+                64
+            ],
+            "vf": [
+                64,
+                64
+            ]
+        },
+        "features_extractor_class": "<class 'imitation.policies.base.NormalizeFeaturesExtractor'>"
+    },
+    "num_timesteps": 1001472,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1694771152613086550,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVXQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJboAAAAAAAAAMhF6NK4PJy/kCYWS7gRpb+T7g30/ZHqP7/vy6bX1O8/mNPHsy7BsD8YO6dh0mlzP+LZQH2EKbS/B4jtdtLztb8AlJRLTM+Uv7JXQL1WvrY/dwZJiZ44qr+AdMTiBOqzv0T+bTcgU7a/0AvgedbpgT/gQL/ZoKmev7LR4l8OYLo/30tBmUrLuT9hk6rYDYKnv+xVDRUsYao/uK6kJH4DtL/9QltLzTjAvxQSVuSk7Kc/bUVeEzFtur+fwQ8KqBmTv6UbSHP3zqu/k7WI5nsagD/7MeLWEK+gP4gME78uLs+/rnQ78tSnoz+UjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLHYaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0014719999999999178,
+    "_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": 4890,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False]",
+        "_shape": [
+            29
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf]",
+        "low_repr": "-inf",
+        "high_repr": "inf",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
+        "low_repr": "-1.0",
+        "high_repr": "1.0",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "n_steps": 2048,
+    "gamma": 0.995,
+    "gae_lambda": 0.8,
+    "ent_coef": 3.1441389214159857e-06,
+    "vf_coef": 0.4351450387648799,
+    "max_grad_norm": 0.9,
+    "batch_size": 16,
+    "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:": "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"
+    }
+}

ppo-seals-Ant-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e77fc689c281acd086c21cff0648e1c0667b5d4f3362633b5b9a3424164ad2
+size 111856

ppo-seals-Ant-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e89b5b04862167f84bdd899f664ea5d8aec65d4604756b3d5bb084a7877d52
+size 57077

ppo-seals-Ant-v1/pytorch_variables.pth

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

ppo-seals-Ant-v1/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": 2461.2202511, "std_reward": 674.8025948179924, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-15T13:50:38.234923"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0727ea96b8c7131a55c58c5a4e8df504f4b31bc89299b2b4bc51224ea5043632
+size 30489

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1148edcbbbfe0bb7b10781159b22198513d93f40d14ee700f6db7986fa8af6
+size 2274