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:
+- MountainCar-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: QRDQN
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -106.50 +/- 10.22
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCar-v0
+      type: MountainCar-v0
+---
+
+# **QRDQN** Agent playing **MountainCar-v0**
+This is a trained model of a **QRDQN** agent playing **MountainCar-v0**
+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 qrdqn --env MountainCar-v0 -orga sb3 -f logs/
+python enjoy.py --algo qrdqn --env MountainCar-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo qrdqn --env MountainCar-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo qrdqn --env MountainCar-v0 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('buffer_size', 10000),
+             ('exploration_final_eps', 0.07),
+             ('exploration_fraction', 0.2),
+             ('gamma', 0.98),
+             ('gradient_steps', 8),
+             ('learning_rate', 0.004),
+             ('learning_starts', 1000),
+             ('n_timesteps', 120000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[256, 256], n_quantiles=25)'),
+             ('target_update_interval', 600),
+             ('train_freq', 16),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - qrdqn
+  - - env
+    - MountainCar-v0
+  - - 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
+    - 643378201
+  - - 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
+    - 128
+  - - buffer_size
+    - 10000
+  - - exploration_final_eps
+    - 0.07
+  - - exploration_fraction
+    - 0.2
+  - - gamma
+    - 0.98
+  - - gradient_steps
+    - 8
+  - - learning_rate
+    - 0.004
+  - - learning_starts
+    - 1000
+  - - n_timesteps
+    - 120000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[256, 256], n_quantiles=25)
+  - - target_update_interval
+    - 600
+  - - train_freq
+    - 16

env_kwargs.yml

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

qrdqn-MountainCar-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd29bcce86b381b4630e793a8f5ce5b856d72fe542c9f3e31eea09ebed07c1c
+size 1400889

qrdqn-MountainCar-v0/_stable_baselines3_version

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

qrdqn-MountainCar-v0/data

@@ -0,0 +1,129 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVLgAAAAAAAACMGnNiM19jb250cmliLnFyZHFuLnBvbGljaWVzlIwLUVJEUU5Qb2xpY3mUk5Qu",
+        "__module__": "sb3_contrib.qrdqn.policies",
+        "__doc__": "\n    Policy class with quantile and target networks for QR-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 n_quantiles: Number of quantiles\n    :param net_arch: The specification of the network architecture.\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 QRDQNPolicy.__init__ at 0x7f40447aa9e0>",
+        "_build": "<function QRDQNPolicy._build at 0x7f40447aaa70>",
+        "make_quantile_net": "<function QRDQNPolicy.make_quantile_net at 0x7f40447aab00>",
+        "forward": "<function QRDQNPolicy.forward at 0x7f40447aab90>",
+        "_predict": "<function QRDQNPolicy._predict at 0x7f40447aac20>",
+        "_get_constructor_parameters": "<function QRDQNPolicy._get_constructor_parameters at 0x7f40447aacb0>",
+        "set_training_mode": "<function QRDQNPolicy.set_training_mode at 0x7f40447aad40>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f40447f9fc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gASVfQAAAAAAAAB9lCiMCG5ldF9hcmNolF2UKE0AAU0AAWWMC25fcXVhbnRpbGVzlEsZjA9vcHRpbWl6ZXJfY2xhc3OUjBB0b3JjaC5vcHRpbS5hZGFtlIwEQWRhbZSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lIwDZXBzlEc/FHrhR64Ue3N1Lg==",
+        "net_arch": [
+            256,
+            256
+        ],
+        "n_quantiles": 25,
+        "optimizer_class": "<class 'torch.optim.adam.Adam'>",
+        "optimizer_kwargs": {
+            "eps": 7.8125e-05
+        }
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": null,
+        "_shape": [
+            2
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": 3,
+        "dtype": "int64",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": []
+    },
+    "n_envs": 1,
+    "num_timesteps": 120000,
+    "_total_timesteps": 120000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614621651.8831997,
+    "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:": "gASVkgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLAoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMIktYMv/DuO7yUdJRiLg=="
+    },
+    "_episode_num": 765,
+    "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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 59504,
+    "buffer_size": 1,
+    "batch_size": 128,
+    "learning_starts": 1000,
+    "tau": 1.0,
+    "gamma": 0.98,
+    "gradient_steps": 8,
+    "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 0x7f4044f93b90>",
+        "add": "<function ReplayBuffer.add at 0x7f4044f93c20>",
+        "sample": "<function ReplayBuffer.sample at 0x7f4044afa7a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f4044afa830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f4044fea5d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLEGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "actor": null,
+    "use_sde_at_warmup": false,
+    "exploration_initial_eps": 1.0,
+    "exploration_final_eps": 0.07,
+    "exploration_fraction": 0.2,
+    "target_update_interval": 600,
+    "max_grad_norm": null,
+    "exploration_rate": 0.07,
+    "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,
+    "n_quantiles": 25
+}

qrdqn-MountainCar-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d7703cbb3e60b4945d69422caa83bd2cb4043b44f5b0ae821a6d65c983009f
+size 689921

qrdqn-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8974431a268d9ff05061c92799447cfea09bb1289219f3929b7fa16c1f18dd89
+size 691073

qrdqn-MountainCar-v0/pytorch_variables.pth

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

qrdqn-MountainCar-v0/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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e902678c61e381104f575fec4b27d972e775a659d91d7a7a992f66d6fc9be08a
+size 260067

results.json

@@ -0,0 +1 @@
+{"mean_reward": -106.5, "std_reward": 10.220078277586722, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T16:36:33.557967"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc3773d6eda24da27ef7d2f536dc3f62a2310dbf61cff182adc7a770addc5696
+size 20290