Initial commit

.gitattributes

@@ -29,3 +29,4 @@ 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 +1,67 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 199.35 +/- 83.29
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+---
+
+# **DQN** Agent playing **LunarLander-v2**
+This is a trained model of a **DQN** 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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo dqn --env LunarLander-v2 -orga theicfire -f logs/
+python enjoy.py --algo dqn --env LunarLander-v2  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo dqn --env LunarLander-v2 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo dqn --env LunarLander-v2 -f logs/ -orga theicfire
+```
+
+## 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)])
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - device
+    - auto
+  - - env
+    - LunarLander-v2
+  - - 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
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 725558725
+  - - 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

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-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17bf98020f411c13cb6039fcc3071ec137968c0a999da70bacaabba23f4e1ed8
+size 1136156

dqn-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.0

dqn-LunarLander-v2/data

@@ -0,0 +1,120 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=",
+        "__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 0x7f6263d219e0>",
+        "_build": "<function DQNPolicy._build at 0x7f6263d21a70>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7f6263d21b00>",
+        "forward": "<function DQNPolicy.forward at 0x7f6263d21b90>",
+        "_predict": "<function DQNPolicy._predict at 0x7f6263d21c20>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7f6263d21cb0>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7f6263d21d40>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f6263d098d0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            256,
+            256
+        ]
+    },
+    "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": 100000,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1661116093.3725772,
+    "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:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRiLg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVqgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLCIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMgt1wtv7Dsyj79hOc8qyFOPbpsxzyUHBm9AAAAAAAAAACUdJRiLg=="
+    },
+    "_episode_num": 207,
+    "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": 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:": "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        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 0x7f62641987a0>",
+        "add": "<function ReplayBuffer.add at 0x7f6264198830>",
+        "sample": "<function ReplayBuffer.sample at 0x7f6264185830>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f62641858c0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f6264200060>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "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,
+    "_n_calls": 100000,
+    "max_grad_norm": 10,
+    "exploration_rate": 0.1,
+    "exploration_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

dqn-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:869e1953c46c02abbc5832896900138db0419ee604c6e9f4517ebe0361ef13c8
+size 557999

dqn-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c30dad6c8343a3eadc97be8ac0d08497312ded3ea2a1309fad5556a14ca5ed9
+size 557057

dqn-LunarLander-v2/pytorch_variables.pth

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

dqn-LunarLander-v2/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
+Python: 3.7.13
+Stable-Baselines3: 1.6.0
+PyTorch: 1.12.1+cu113
+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:b9d1ab82cf4bd9482b5e90d57f6cc8b564a5e92fbf8ac90083ce7fa29399b193
+size 220375

results.json

@@ -0,0 +1 @@
+{"mean_reward": 199.3534916, "std_reward": 83.29014755347582, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-21T21:22:02.364443"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac3a6a19ee3f09ea01d4a30a7cced63eddcce82c2ec4f27d094024d0c973668
+size 6836