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

@@ -16,22 +16,69 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 81.57 +/- 110.80
+      value: 184.85 +/- 106.23
       name: mean_reward
       verified: false
 ---
 
 # **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).
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
 
-## Usage (with Stable-baselines3)
-TODO: Add your code
+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 LunarLander-v2 -orga nsanghi -f logs/
+python -m rl_zoo3.enjoy --algo dqn --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 dqn --env LunarLander-v2 -orga nsanghi -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env LunarLander-v2  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo dqn --env LunarLander-v2 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo dqn --env LunarLander-v2 -f logs/ -orga nsanghi
+```
+
+## Hyperparameters
 ```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+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 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - LunarLander-v2
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - 400
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 1
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - 100000
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - true
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1726845707
+  - - 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-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:485a6dbde6556f7eac7d097f61abb5291917692453cad714841309ec0198b038
-size 105299
+oid sha256:cfdac5700c8cb088fd8d75b3cce587e30609f986dcc005dc741f8bbffb1678bc
+size 1132221

dqn-LunarLander-v2/data

@@ -5,84 +5,57 @@
         "__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 0x7f8bd040c9d0>",
-        "_build": "<function DQNPolicy._build at 0x7f8bd040ca60>",
-        "make_q_net": "<function DQNPolicy.make_q_net at 0x7f8bd040caf0>",
-        "forward": "<function DQNPolicy.forward at 0x7f8bd040cb80>",
-        "_predict": "<function DQNPolicy._predict at 0x7f8bd040cc10>",
-        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7f8bd040cca0>",
-        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7f8bd040cd30>",
+        "__init__": "<function DQNPolicy.__init__ at 0x7fc6d8cf52d0>",
+        "_build": "<function DQNPolicy._build at 0x7fc6d8cf5360>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7fc6d8cf53f0>",
+        "forward": "<function DQNPolicy.forward at 0x7fc6d8cf5480>",
+        "_predict": "<function DQNPolicy._predict at 0x7fc6d8cf5510>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7fc6d8cf55a0>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7fc6d8cf5630>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f8bd0414100>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fc6d8ceeb00>"
     },
     "verbose": 1,
-    "policy_kwargs": {},
+    "policy_kwargs": {
+        "net_arch": [
+            256,
+            256
+        ]
+    },
     "num_timesteps": 100000,
     "_total_timesteps": 100000,
     "_num_timesteps_at_start": 0,
-    "seed": null,
+    "seed": 0,
     "action_noise": null,
-    "start_time": 1688986566359833733,
-    "learning_rate": 0.0001,
-    "tensorboard_log": null,
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAIBwcb3jUKU/MoRBvSUv8L2zXaG9rnl9PAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+    "start_time": 1689226241621930794,
+    "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:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAE2Jb71jp6U/MIRBvRySub1D86K9xXl9PAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAE2kA74UiPq6d6W0OXd9bTbpJNA7AMDRuAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
-    "_episode_num": 619,
+    "_episode_num": 222,
     "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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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 12500,
-    "buffer_size": 1000000,
-    "batch_size": 32,
-    "learning_starts": 50000,
-    "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 0x7f8bd05e8ee0>",
-        "add": "<function ReplayBuffer.add at 0x7f8bd05e8f70>",
-        "sample": "<function ReplayBuffer.sample at 0x7f8bd05e9000>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f8bd05e9090>",
-        "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f8bd05e5d80>"
-    },
-    "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": 0.1,
-    "target_update_interval": 250,
-    "_n_calls": 100000,
-    "max_grad_norm": 10,
-    "exploration_rate": 0.1,
+    "_n_updates": 100000,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -100,7 +73,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "n": "4",
         "start": "0",
         "_shape": [],
@@ -108,14 +81,46 @@
         "_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",
+        "__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 0x7fc6d8cd1900>",
+        "add": "<function ReplayBuffer.add at 0x7fc6d8cd1990>",
+        "sample": "<function ReplayBuffer.sample at 0x7fc6d8cd1a20>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fc6d8cd1ab0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fc6d8c33a80>"
+    },
+    "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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"
+        ":serialized:": "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"
     },
     "batch_norm_stats": [],
     "batch_norm_stats_target": [],
     "exploration_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     }
 }

dqn-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1ac85e7ae0e0359bdb44250fadde60cedf1e082f0151d830e134f1a30b2a68
-size 44783
+oid sha256:c11d80a76d092f0643ef836526fc2c64cf7152d0d25388c724b09ad0af8144e2
+size 557807

dqn-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99b0f6bc005ff5c3a33f888176a62634783f4ad2bdd36d11f3d279052f32ceb4
-size 43905
+oid sha256:9ff395ed24820c27ec3278505cce70c072d06ce0eb7461ce77518eb7c209d3e7
+size 556929

env_kwargs.yml

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

results.json

@@ -1 +1 @@
-{"mean_reward": 81.57284787867836, "std_reward": 110.79918998503821, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-10T16:29:54.380247"}
+{"mean_reward": 184.85006360000003, "std_reward": 106.23244927226477, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-13T11:49:09.551113"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:074dfef77b610b76d89bda050ba25179d6903894d81006b42200559835aa19bd
+size 7273