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:
+- Acrobot-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: QRDQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Acrobot-v1
+      type: Acrobot-v1
+    metrics:
+    - type: mean_reward
+      value: -86.40 +/- 23.60
+      name: mean_reward
+      verified: false
+---
+
+# **QRDQN** Agent playing **Acrobot-v1**
+This is a trained model of a **QRDQN** agent playing **Acrobot-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
+
+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 Acrobot-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo qrdqn --env Acrobot-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 qrdqn --env Acrobot-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo qrdqn --env Acrobot-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo qrdqn --env Acrobot-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo qrdqn --env Acrobot-v1 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('buffer_size', 50000),
+             ('exploration_final_eps', 0.1),
+             ('exploration_fraction', 0.12),
+             ('gamma', 0.99),
+             ('gradient_steps', -1),
+             ('learning_rate', 0.00063),
+             ('learning_starts', 0),
+             ('n_timesteps', 100000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[256, 256], n_quantiles=25)'),
+             ('target_update_interval', 250),
+             ('train_freq', 4),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,79 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - qrdqn
+  - - device
+    - auto
+  - - env
+    - Acrobot-v1
+  - - 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
+    - 2309622469
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Acrobot-v1__qrdqn__2309622469__1670942910
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,27 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 128
+  - - buffer_size
+    - 50000
+  - - exploration_final_eps
+    - 0.1
+  - - exploration_fraction
+    - 0.12
+  - - gamma
+    - 0.99
+  - - gradient_steps
+    - -1
+  - - learning_rate
+    - 0.00063
+  - - learning_starts
+    - 0
+  - - n_timesteps
+    - 100000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[256, 256], n_quantiles=25)
+  - - target_update_interval
+    - 250
+  - - train_freq
+    - 4

env_kwargs.yml

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

qrdqn-Acrobot-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef9436a170f3d46479bde20ca11903b68855f43529a692f453765b490a088cf
+size 1419361

qrdqn-Acrobot-v1/_stable_baselines3_version

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

qrdqn-Acrobot-v1/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 0x7f48962d3820>",
+        "_build": "<function QRDQNPolicy._build at 0x7f48962d38b0>",
+        "make_quantile_net": "<function QRDQNPolicy.make_quantile_net at 0x7f48962d3940>",
+        "forward": "<function QRDQNPolicy.forward at 0x7f48962d39d0>",
+        "_predict": "<function QRDQNPolicy._predict at 0x7f48962d3a60>",
+        "_get_constructor_parameters": "<function QRDQNPolicy._get_constructor_parameters at 0x7f48962d3af0>",
+        "set_training_mode": "<function QRDQNPolicy.set_training_mode at 0x7f48962d3b80>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f48962d6800>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVfQAAAAAAAAB9lCiMCG5ldF9hcmNolF2UKE0AAU0AAWWMC25fcXVhbnRpbGVzlEsZjA9vcHRpbWl6ZXJfY2xhc3OUjBB0b3JjaC5vcHRpbS5hZGFtlIwEQWRhbZSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lIwDZXBzlEc/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",
+        "_shape": [
+            6
+        ],
+        "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]",
+        "high": "[ 1.        1.        1.        1.       12.566371 28.274334]",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": 3,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 100000,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1670942912295672899,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/Acrobot-v1__qrdqn__2309622469__1670942910/Acrobot-v1",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWV/QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZS9ob21lL3FnYWxsb3VlZGVjL3JsLWJhc2VsaW5lczMtem9vL2Vudi9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxlL2hvbWUvcWdhbGxvdWVkZWMvcmwtYmFzZWxpbmVzMy16b28vZW52L2xpYi9weXRob24zLjkvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP0Sk0rK/202FlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVjQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYYAAAAAAAAAEuXCz/tl1Y/izN8v8y/L75jZTHAj2yNQJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsGhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 1041,
+    "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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 100000,
+    "buffer_size": 1,
+    "batch_size": 128,
+    "learning_starts": 0,
+    "tau": 1.0,
+    "gamma": 0.99,
+    "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 0x7f489676a430>",
+        "add": "<function ReplayBuffer.add at 0x7f489676a4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f489676a550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f489676a5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f4896761c00>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "actor": null,
+    "use_sde_at_warmup": false,
+    "exploration_initial_eps": 1.0,
+    "exploration_final_eps": 0.1,
+    "exploration_fraction": 0.12,
+    "target_update_interval": 250,
+    "max_grad_norm": null,
+    "exploration_rate": 0.1,
+    "exploration_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVYQMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLBEsTQyxkAXwAGACIAWsEchCIAFMAiAJkAXwAGACIAIgCGAAUAIgBGwAXAFMAZABTAJROSwGGlCmMEnByb2dyZXNzX3JlbWFpbmluZ5SFlIxFL2hvbWUvcWdhbGxvdWVkZWMvc3RhYmxlLWJhc2VsaW5lczMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLcEMGAAEMAQQClIwDZW5klIwMZW5kX2ZyYWN0aW9ulIwFc3RhcnSUh5QpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxFL2hvbWUvcWdhbGxvdWVkZWMvc3RhYmxlLWJhc2VsaW5lczMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUaB0pUpRoHSlSlIeUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgjfZR9lChoGGgNjAxfX3F1YWxuYW1lX1+UjBtnZXRfbGluZWFyX2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZQoaAqMCGJ1aWx0aW5zlIwFZmxvYXSUk5SMBnJldHVybpRoL3WMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgZjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz+5mZmZmZmahZRSlGg3Rz++uFHrhR64hZRSlGg3Rz/wAAAAAAAAhZRSlIeUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "n_quantiles": 25,
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

qrdqn-Acrobot-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdeaa5af644f33b967d1517b1e7bc0a57b278c449d48931c6acd906894852c5
+size 699823

qrdqn-Acrobot-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e86e8a451ff85b4861908f6c19615a3d127705bd8327f1ba400d06e61b368ec
+size 699265

qrdqn-Acrobot-v1/pytorch_variables.pth

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

qrdqn-Acrobot-v1/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:b1ae566ce59e8a98431d78f416a6228d56cf26a9fc8d3c643b5354d73e1f6c40
+size 922626

results.json

@@ -0,0 +1 @@
+{"mean_reward": -86.4, "std_reward": 23.59745749016194, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:03:36.811817"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08d13789873b8fca216db69edd989a6af51d0d5380dcc17759c341cd77c462b
+size 24240