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 +1,81 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLanderContinuous-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLanderContinuous-v2
+      type: LunarLanderContinuous-v2
+    metrics:
+    - type: mean_reward
+      value: -25.50 +/- 105.78
+      name: mean_reward
+      verified: false
+---
+
+# **A2C** Agent playing **LunarLanderContinuous-v2**
+This is a trained model of a **A2C** agent playing **LunarLanderContinuous-v2**
+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 LunarLanderContinuous-v2 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo a2c --env LunarLanderContinuous-v2  -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 LunarLanderContinuous-v2 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo a2c --env LunarLanderContinuous-v2  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo a2c --env LunarLanderContinuous-v2 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo a2c --env LunarLanderContinuous-v2 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('ent_coef', 0.0),
+             ('gae_lambda', 0.9),
+             ('gamma', 0.99),
+             ('learning_rate', 'lin_7e-4'),
+             ('max_grad_norm', 0.5),
+             ('n_envs', 4),
+             ('n_steps', 8),
+             ('n_timesteps', 5000000.0),
+             ('normalize', True),
+             ('normalize_advantage', False),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-2, ortho_init=False)'),
+             ('use_rms_prop', True),
+             ('use_sde', True),
+             ('vf_coef', 0.4),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

a2c-LunarLanderContinuous-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d56258b839f346d752b6c725fec719a5e76fe59f1cce1076e1ab08e4b3c681
+size 107052

a2c-LunarLanderContinuous-v2/_stable_baselines3_version

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

a2c-LunarLanderContinuous-v2/data

@@ -0,0 +1,106 @@
+{
+    "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 0x7fa106c4fd30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa106c4fdc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa106c4fe50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa106c4fee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fa106c4ff70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fa106c51040>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa106c510d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa106c51160>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fa106c511f0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa106c51280>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa106c51310>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa106c513a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fa106c50f80>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu",
+        "log_std_init": -2,
+        "ortho_init": false,
+        "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": [
+            8
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1. -1.]",
+        "high": "[1. 1.]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 5000000,
+    "_total_timesteps": 5000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1670923575747221069,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/LunarLanderContinuous-v2__a2c__1809578713__1670923573/LunarLanderContinuous-v2",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAGamnTnJubQ/wEv5PK35NT2xELO5cuDhuwAAAAAAAAAAmglau6SftD+ejKy+EPsSPKwZfTsIV5w9AAAAAAAAAACatc67/qW1P+WTI7/3xLo+UL/vOwo2FD4AAAAAAAAAAGZu5zsQ9LM/JiI3P1cjZb59+QW8BO4lvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwiGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 0,
+    "use_sde": true,
+    "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": 156250,
+    "n_steps": 8,
+    "gamma": 0.99,
+    "gae_lambda": 0.9,
+    "ent_coef": 0.0,
+    "vf_coef": 0.4,
+    "max_grad_norm": 0.5,
+    "normalize_advantage": false
+}

a2c-LunarLanderContinuous-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99996ff27f28075788b682a402a4832d7b450bcdeb7ebc747962cf9ed77e80d8
+size 42878

a2c-LunarLanderContinuous-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdbc82ac63422952ebfe54015e30608cb4a99275cd07caf2fc6f5870c275f8ae
+size 43582

a2c-LunarLanderContinuous-v2/pytorch_variables.pth

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

a2c-LunarLanderContinuous-v2/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
+    - LunarLanderContinuous-v2
+  - - 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
+    - 1809578713
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/LunarLanderContinuous-v2__a2c__1809578713__1670923573
+  - - 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 +1,31 @@
+!!python/object/apply:collections.OrderedDict
+- - - ent_coef
+    - 0.0
+  - - gae_lambda
+    - 0.9
+  - - gamma
+    - 0.99
+  - - learning_rate
+    - lin_7e-4
+  - - max_grad_norm
+    - 0.5
+  - - n_envs
+    - 4
+  - - n_steps
+    - 8
+  - - n_timesteps
+    - 5000000.0
+  - - normalize
+    - true
+  - - normalize_advantage
+    - false
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-2, ortho_init=False)
+  - - use_rms_prop
+    - true
+  - - use_sde
+    - true
+  - - vf_coef
+    - 0.4

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093e2e8be3ef5e851532728e3a84ba1317a0af7047644c47b1018d139780eb50
+size 255693

results.json

@@ -0,0 +1 @@
+{"mean_reward": -25.5006485, "std_reward": 105.7824751432848, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:49:08.198048"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bca459128241285cfcba045bec109285de61b2f1603705848c3dbcf089bbea
+size 287358

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c0905ed74eb5a9086cc93d0d9cf70e9a265f2dad074a338f07b8ccf2985e4b
+size 4323