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: 500.00 +/- 0.00
+      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 sb3 -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 sb3
+```
+
+## 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 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - env
+    - CartPole-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - rl-trained-agents/
+  - - log_interval
+    - -1
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - num_threads
+    - -1
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1017579432
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

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 sha256:0a32abde4c74fd5bee815e55433b348798c3358c01af66ee3084404405c80189
+size 1108385

dqn-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a8

dqn-CartPole-v1/data

@@ -0,0 +1,122 @@
+{
+    "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 0x7f020a2d27a0>",
+        "_build": "<function DQNPolicy._build at 0x7f020a2d2830>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7f020a2d28c0>",
+        "forward": "<function DQNPolicy.forward at 0x7f020a2d2950>",
+        "_predict": "<function DQNPolicy._predict at 0x7f020a2d29e0>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7f020a2d2a70>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7f020a2d2b00>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f020a2c1630>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            256,
+            256
+        ]
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "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,
+        "_shape": [
+            4
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": 2,
+        "dtype": "int64",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": []
+    },
+    "n_envs": 1,
+    "num_timesteps": 50176,
+    "_total_timesteps": 50000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614621403.8873796,
+    "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": null,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVmgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLBIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMQRGSlOdwXQz9OhCA+HaSDvZR0lGIu"
+    },
+    "_episode_num": 500,
+    "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 0x7f020a740b90>",
+        "add": "<function ReplayBuffer.add at 0x7f020a740c20>",
+        "sample": "<function ReplayBuffer.sample at 0x7f020a2a77a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f020a2a7830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f020a7975d0>"
+    },
+    "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": 0,
+    "max_grad_norm": 10,
+    "exploration_rate": 0.04,
+    "exploration_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "remove_time_limit_termination": false
+}

dqn-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca8d0cb074b35ef2f0aba7adbe1b622ee2291a30b0a631bdc98c8e2ae7470fc6
+size 544001

dqn-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448722f6339b692ed6f27817c6817a962bdb158f60bd4bcbb66a8ca802389b3e
+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-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
+Python: 3.7.10
+Stable-Baselines3: 1.5.1a8
+PyTorch: 1.11.0
+GPU Enabled: True
+Numpy: 1.21.2
+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:bd5f14a3044600142b3fc154eaa482661f0f2524dabf85563d664cb17df7fe94
+size 100571

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T20:30:47.543802"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d91965f44dcd4177fb637ca0c838e32461af48b4fb4da2d23981669383c8fdd
+size 11630