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 +1,74 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  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
+---
+
+# **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 rl_zoo3.load_from_hub --algo dqn --env CartPole-v1 -orga sryu1 -f logs/
+python enjoy.py --algo dqn --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 dqn --env CartPole-v1 -orga sryu1 -f logs/
+rl_zoo3 enjoy --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 rl_zoo3.push_to_hub --algo dqn --env CartPole-v1 -f logs/ -orga sryu1
+```
+
+## 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 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - conf_file
+    - null
+  - - 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
+    - 2863598343
+  - - 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
+  - - yaml_file
+    - null

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 sha256:9e938eb3a70ce866961fa00630782089f4c73ddc1c45e28582eb180a4c39dbaa
+size 1109969

dqn-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.2

dqn-CartPole-v1/data

@@ -0,0 +1,122 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=",
+        "__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 0x7fac440489d0>",
+        "_build": "<function DQNPolicy._build at 0x7fac44048a60>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7fac44048af0>",
+        "forward": "<function DQNPolicy.forward at 0x7fac44048b80>",
+        "_predict": "<function DQNPolicy._predict at 0x7fac44048c10>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7fac44048ca0>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7fac44048d30>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fac43bc7420>"
+    },
+    "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": 1671534893658669932,
+    "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:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAC5Roz0q8Pe7/xhBPAlcIr2UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 455,
+    "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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_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:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__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: PyTorch 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        Cannot be used in combination with handle_timeout_termination.\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 0x7fac4402f9d0>",
+        "add": "<function ReplayBuffer.add at 0x7fac4402fa60>",
+        "sample": "<function ReplayBuffer.sample at 0x7fac4402faf0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fac4402fb80>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fac440b8990>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYgAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RNAAFoAIwSVHJhaW5GcmVxdWVuY3lVbml0lJOUjARzdGVwlIWUUpSGlIGULg=="
+    },
+    "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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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

dqn-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b0c071d6354b7a1adf45535c49541e7482fd2a1c159334acd7b33bc384f778
+size 545711

dqn-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b92eed740a94e3622b5355082302e924dafd579ad991a25dc86dd03f75a214
+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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
+Python: 3.8.16
+Stable-Baselines3: 1.6.2
+PyTorch: 1.13.0+cu116
+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:e185b22d2ce2911c1a57d5d0e36ab674980b5dbce9909b54c8ec86d73ab5d0f0
+size 66157

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T11:18:09.780426"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db699fe1dd20c5b08df6c523867a51eca7a36d44976a8367c29435a0c1c69ad6
+size 10150