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 +1,67 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 117.00 +/- 2.65
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+---
+
+# **DQN** Agent playing **CartPole-v1**
+This is a trained model of a **DQN** 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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo dqn --env CartPole-v1 -orga epsil -f logs/
+python enjoy.py --algo dqn --env CartPole-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo dqn --env CartPole-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo dqn --env CartPole-v1 -f logs/ -orga epsil
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 64),
+             ('buffer_size', 100000),
+             ('exploration_final_eps', 0.04),
+             ('exploration_fraction', 0.16),
+             ('gamma', 0.99),
+             ('gradient_steps', 128),
+             ('learning_rate', 0.0023),
+             ('learning_starts', 1000),
+             ('n_timesteps', 50000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[256, 256])'),
+             ('target_update_interval', 10),
+             ('train_freq', 256),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - 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
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 2843595907
+  - - 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

config.yml

@@ -0,0 +1,27 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 64
+  - - buffer_size
+    - 100000
+  - - exploration_final_eps
+    - 0.04
+  - - exploration_fraction
+    - 0.16
+  - - gamma
+    - 0.99
+  - - gradient_steps
+    - 128
+  - - learning_rate
+    - 0.0023
+  - - learning_starts
+    - 1000
+  - - n_timesteps
+    - 50000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[256, 256])
+  - - target_update_interval
+    - 10
+  - - train_freq
+    - 256

dqn-CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c038a013843b8e9422b34310c13d397e7bb83689991f75e047bc62ade802e416
+size 1108229

dqn-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a7

dqn-CartPole-v1/data

@@ -0,0 +1,120 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.dqn.policies",
+        "__doc__": "\n    Policy class with Q-Value Net and target net for DQN\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 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 DQNPolicy.__init__ at 0x7f0e2f7d2950>",
+        "_build": "<function DQNPolicy._build at 0x7f0e2f7d29e0>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7f0e2f7d2a70>",
+        "forward": "<function DQNPolicy.forward at 0x7f0e2f7d2b00>",
+        "_predict": "<function DQNPolicy._predict at 0x7f0e2f7d2b90>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7f0e2f7d2c20>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7f0e2f7d2cb0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f0e2fc4d7e0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            256,
+            256
+        ]
+    },
+    "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": 50176,
+    "_total_timesteps": 50000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1654678072.0081553,
+    "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:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRiLg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVmgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLBIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMQpLjePYGuP7+rLlO+oL0lPpR0lGIu"
+    },
+    "_episode_num": 459,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0035199999999999676,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 24704,
+    "buffer_size": 1,
+    "batch_size": 64,
+    "learning_starts": 1000,
+    "tau": 1.0,
+    "gamma": 0.99,
+    "gradient_steps": 128,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device:\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7f0e2fc59710>",
+        "add": "<function ReplayBuffer.add at 0x7f0e2fc597a0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f0e2fc3e7a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f0e2fc3e830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f0e2fd12f30>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYgAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RNAAFoAIwSVHJhaW5GcmVxdWVuY3lVbml0lJOUjARzdGVwlIWUUpSGlIGULg=="
+    },
+    "actor": null,
+    "use_sde_at_warmup": false,
+    "exploration_initial_eps": 1.0,
+    "exploration_final_eps": 0.04,
+    "exploration_fraction": 0.16,
+    "target_update_interval": 10,
+    "_n_calls": 50176,
+    "max_grad_norm": 10,
+    "exploration_rate": 0.04,
+    "exploration_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

dqn-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ac8f3cc5c454d61bb9da83f8606c0dea34c6734ddbcff1b77be53bb411c748
+size 544001

dqn-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d50621f198bb7050448dae51e6aa0c84665da18e7db4e978174b45e6bb6e4ed8
+size 544769

dqn-CartPole-v1/pytorch_variables.pth

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

dqn-CartPole-v1/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
+Python: 3.7.13
+Stable-Baselines3: 1.5.1a7
+PyTorch: 1.11.0+cu113
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a459bb04b76e26ee290e43a0f4dcfa2c154ceb9e70ea3f9db6f7ff3c1481cfd6
+size 108971

results.json

@@ -0,0 +1 @@
+{"mean_reward": 117.0, "std_reward": 2.6457513110645907, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-08T09:02:14.115384"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9e1f748a307ea172720458a187564465cf869bcff972cd1c2abdc4e31fce97
+size 10337