Initial commit

.gitattributes

@@ -33,3 +33,4 @@ 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 +1,84 @@
+---
+library_name: stable-baselines3
+tags:
+- Acrobot-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Acrobot-v1
+      type: Acrobot-v1
+    metrics:
+    - type: mean_reward
+      value: -500.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **DQN** Agent playing **Acrobot-v1**
+This is a trained model of a **DQN** 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 dqn --env Acrobot-v1 -orga dlantonia -f logs/
+python -m rl_zoo3.enjoy --algo dqn --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 dqn --env Acrobot-v1 -orga dlantonia -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env Acrobot-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo dqn --env Acrobot-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo dqn --env Acrobot-v1 -f logs/ -orga dlantonia
+```
+
+## 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])'),
+             ('target_update_interval', 250),
+             ('train_freq', 4),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - Acrobot-v1
+  - - env_kwargs
+    - null
+  - - eval_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
+    - 3524042168
+  - - 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
+  - - wandb_tags
+    - []

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])
+  - - target_update_interval
+    - 250
+  - - train_freq
+    - 4

dqn-Acrobot-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf45e97f17b5161d8d28e1d74ce10823fb8b3e8c80110abef1e695e461868adf
+size 1121979

dqn-Acrobot-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.4.0a7

dqn-Acrobot-v1/data

@@ -0,0 +1,128 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.dqn.policies",
+        "__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}",
+        "__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 0x7fe2bd786560>",
+        "_build": "<function DQNPolicy._build at 0x7fe2bd7865f0>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7fe2bd786680>",
+        "forward": "<function DQNPolicy.forward at 0x7fe2bd786710>",
+        "_predict": "<function DQNPolicy._predict at 0x7fe2bd7867a0>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7fe2bd786830>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7fe2bd7868c0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fe2bd78bec0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            256,
+            256
+        ]
+    },
+    "num_timesteps": 100000,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1723040556991871906,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVjQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYYAAAAAAAAAGteUD8CuRQ/NSAyPwreN7874FW/ylOTP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsGhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 1004,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 100000,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_shape": [
+            6
+        ],
+        "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]",
+        "high": "[ 1.        1.        1.        1.       12.566371 28.274334]",
+        "low_repr": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]",
+        "high_repr": "[ 1.        1.        1.        1.       12.566371 28.274334]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVwAEAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwQX19nZW5lcmF0b3JfY3RvcpSTlIwFUENHNjSUaB+MFF9fYml0X2dlbmVyYXRvcl9jdG9ylJOUhpRSlH2UKIwNYml0X2dlbmVyYXRvcpSMBVBDRzY0lIwFc3RhdGWUfZQoaCqKEONhlaa3XlgJLUWWWTS1oRqMA2luY5SKEKlzeES8M4FYghr3OtvajUF1jApoYXNfdWludDMylEsAjAh1aW50ZWdlcpRLAHVidWIu",
+        "n": "3",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "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",
+        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
+        "__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 0x7fe2bd8cbc70>",
+        "add": "<function ReplayBuffer.add at 0x7fe2bd8cbd00>",
+        "sample": "<function ReplayBuffer.sample at 0x7fe2bd8cbd90>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fe2bd8cbe20>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fe2bd8cbeb0>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fe2bdaa0440>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "exploration_initial_eps": 1.0,
+    "exploration_final_eps": 0.1,
+    "exploration_fraction": 0.12,
+    "target_update_interval": 250,
+    "_n_calls": 100000,
+    "max_grad_norm": 10,
+    "exploration_rate": 0.1,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": [],
+    "exploration_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

dqn-Acrobot-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f396a973515c9df4e2039e19bfb8aa86ad2afd825667b294006624a5d7ea2a
+size 552288

dqn-Acrobot-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da499005ee4c75118c35d6ad8c3fe9f0eaade4a54e2d8b4f7530baa970eaf35
+size 551346

dqn-Acrobot-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

dqn-Acrobot-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
+- Python: 3.10.12
+- Stable-Baselines3: 2.4.0a7
+- PyTorch: 2.3.1+cu121
+- GPU Enabled: True
+- Numpy: 1.26.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.26.2

env_kwargs.yml

@@ -0,0 +1 @@
+render_mode: rgb_array

results.json

@@ -0,0 +1 @@
+{"mean_reward": -500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-07T14:28:27.969199"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4412ff081b7a60b65bfcb1637229ad40a473c7fab449b3690d714eb313d0f254
+size 22737