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 +1,79 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: QRDQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 212.07 +/- 41.92
+      name: mean_reward
+      verified: false
+---
+
+# **QRDQN** Agent playing **LunarLander-v2**
+This is a trained model of a **QRDQN** agent playing **LunarLander-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 qrdqn --env LunarLander-v2 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo qrdqn --env LunarLander-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 qrdqn --env LunarLander-v2 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo qrdqn --env LunarLander-v2  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo qrdqn --env LunarLander-v2 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo qrdqn --env LunarLander-v2 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('buffer_size', 100000),
+             ('exploration_final_eps', 0.18),
+             ('exploration_fraction', 0.24),
+             ('gamma', 0.995),
+             ('gradient_steps', -1),
+             ('learning_rate', 'lin_1.5e-3'),
+             ('learning_starts', 10000),
+             ('n_timesteps', 100000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[256, 256], n_quantiles=170)'),
+             ('target_update_interval', 1),
+             ('train_freq', 256),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - qrdqn
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - LunarLander-v2
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 5
+  - - 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
+    - 3752531572
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/LunarLander-v2__qrdqn__3752531572__1677081765
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,27 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 128
+  - - buffer_size
+    - 100000
+  - - exploration_final_eps
+    - 0.18
+  - - exploration_fraction
+    - 0.24
+  - - gamma
+    - 0.995
+  - - gradient_steps
+    - -1
+  - - learning_rate
+    - lin_1.5e-3
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 100000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[256, 256], n_quantiles=170)
+  - - target_update_interval
+    - 1
+  - - train_freq
+    - 256

env_kwargs.yml

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

qrdqn-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755399941c21357c60ebd3a7619af223d9aff6793841c9d0a9a1227d2ff5083c
+size 3917231

qrdqn-LunarLander-v2/_stable_baselines3_version

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

qrdqn-LunarLander-v2/data

@@ -0,0 +1,129 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVLgAAAAAAAACMGnNiM19jb250cmliLnFyZHFuLnBvbGljaWVzlIwLUVJEUU5Qb2xpY3mUk5Qu",
+        "__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 0x7faee62d3820>",
+        "_build": "<function QRDQNPolicy._build at 0x7faee62d38b0>",
+        "make_quantile_net": "<function QRDQNPolicy.make_quantile_net at 0x7faee62d3940>",
+        "forward": "<function QRDQNPolicy.forward at 0x7faee62d39d0>",
+        "_predict": "<function QRDQNPolicy._predict at 0x7faee62d3a60>",
+        "_get_constructor_parameters": "<function QRDQNPolicy._get_constructor_parameters at 0x7faee62d3af0>",
+        "set_training_mode": "<function QRDQNPolicy.set_training_mode at 0x7faee62d3b80>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7faee62d4940>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVfQAAAAAAAAB9lCiMCG5ldF9hcmNolF2UKE0AAU0AAWWMC25fcXVhbnRpbGVzlEuqjA9vcHRpbWl6ZXJfY2xhc3OUjBB0b3JjaC5vcHRpbS5hZGFtlIwEQWRhbZSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lIwDZXBzlEc/FHrhR64Ue3N1Lg==",
+        "net_arch": [
+            256,
+            256
+        ],
+        "n_quantiles": 170,
+        "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",
+        "_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.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 100096,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1677081768403859578,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/LunarLander-v2__qrdqn__3752531572__1677081765/LunarLander-v2",
+    "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:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM0cYLxcW2W6mvD8umUdHbn9WxQ6S8oSOgAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 263,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0009600000000000719,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 90112,
+    "buffer_size": 1,
+    "batch_size": 128,
+    "learning_starts": 10000,
+    "tau": 1.0,
+    "gamma": 0.995,
+    "gradient_steps": -1,
+    "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 0x7faee676a430>",
+        "add": "<function ReplayBuffer.add at 0x7faee676a4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7faee676a550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7faee676a5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7faee6761980>"
+    },
+    "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": 0.18,
+    "exploration_fraction": 0.24,
+    "target_update_interval": 1,
+    "max_grad_norm": null,
+    "exploration_rate": 0.18,
+    "exploration_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "n_quantiles": 170,
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

qrdqn-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c455aaf915612d1f8e3a27b9e8bb200377300fa9a1de5f47267a235a71da8f
+size 1947823

qrdqn-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e43f4a48cd8a3bedbbe7a8b57b6ecae2cfa4925c0bedcbbd8c56399bbd9697
+size 1947265

qrdqn-LunarLander-v2/pytorch_variables.pth

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

qrdqn-LunarLander-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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5016fe81f2653273533dae59b351b2d9177e8f13273b71f874479e8b6e3dee9
+size 215181

results.json

@@ -0,0 +1 @@
+{"mean_reward": 212.0655474, "std_reward": 41.924509415511444, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:02:25.673004"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96563bb8150e0619c81ee071398d13347a89dbba0236f7bc056f13d214e97669
+size 9210