Initial commit

.gitattributes

@@ -32,3 +32,4 @@ 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 +1,70 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 500.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **A2C** Agent playing **CartPole-v1**
+This is a trained model of a **A2C** agent playing **CartPole-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 a2c --env CartPole-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo a2c --env CartPole-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 a2c --env CartPole-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo a2c --env CartPole-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo a2c --env CartPole-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo a2c --env CartPole-v1 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('ent_coef', 0.0),
+             ('n_envs', 8),
+             ('n_timesteps', 500000.0),
+             ('policy', 'MlpPolicy'),
+             ('normalize', False)])
+```

a2c-CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c78d095c2d0f8a745ce4a3ff69b95a4ba6ef841f9865679944d42398363150
+size 97571

a2c-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

a2c-CartPole-v1/data

@@ -0,0 +1,93 @@
+{
+    "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 0x7fd4ef090d30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd4ef090dc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd4ef090e50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd4ef090ee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fd4ef090f70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fd4ef092040>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd4ef0920d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd4ef092160>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fd4ef0921f0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd4ef092280>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd4ef092310>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd4ef0923a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fd4ef08e940>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
+        "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
+        "optimizer_kwargs": {
+            "alpha": 0.99,
+            "eps": 1e-05,
+            "weight_decay": 0
+        }
+    },
+    "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:": "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",
+        "n": 2,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 500000,
+    "_total_timesteps": 500000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1670922857229289067,
+    "learning_rate": 0.0007,
+    "tensorboard_log": "runs/CartPole-v1__a2c__257778613__1670922854/CartPole-v1",
+    "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": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 12500,
+    "n_steps": 5,
+    "gamma": 0.99,
+    "gae_lambda": 1.0,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "normalize_advantage": false
+}

a2c-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4914a74eb0db6606d850dde04fa2c0a3dfb89b79ef8ba4ebbf1bf35dde320e
+size 40065

a2c-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45961902d68812d7c3a6555c3c923348f47ba9abaf6954b2e3a0f32b703962bb
+size 40769

a2c-CartPole-v1/pytorch_variables.pth

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

a2c-CartPole-v1/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

args.yml

@@ -0,0 +1,79 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - a2c
+  - - device
+    - auto
+  - - env
+    - CartPole-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - 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
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 257778613
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/CartPole-v1__a2c__257778613__1670922854
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - quantitative-benchmark
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,9 @@
+!!python/object/apply:collections.OrderedDict
+- - - ent_coef
+    - 0.0
+  - - n_envs
+    - 8
+  - - n_timesteps
+    - 500000.0
+  - - policy
+    - MlpPolicy

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd99bec84b4aa06f7ad5756e366530ed23c2a1488e12159daaa4553fdac8bfc
+size 55985

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:55:31.027880"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39e059c232975a806622dbb6139555192b7e76c39c2f59eccb6125694ca1d8c
+size 38283