Initial commit

README.md

@@ -16,22 +16,69 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 87.35 +/- 35.51
+      value: -188.60 +/- 65.20
       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

@@ -54,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 2545653355
+    - 43775958
   - - storage
     - null
   - - study_name

dqn-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b213dd6ac78a6ad81330151a21fbfd198a7c9bbc49e50de9571ac38895fe0f48
-size 106438
+oid sha256:5434239906637146bfba1c0afb18b5d53a3d9ca0fbbc0a45938785806f1371e2
+size 1133414

dqn-LunarLander-v2/data

@@ -5,85 +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 0x7f7bc1685040>",
-        "_build": "<function DQNPolicy._build at 0x7f7bc16850d0>",
-        "make_q_net": "<function DQNPolicy.make_q_net at 0x7f7bc1685160>",
-        "forward": "<function DQNPolicy.forward at 0x7f7bc16851f0>",
-        "_predict": "<function DQNPolicy._predict at 0x7f7bc1685280>",
-        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7f7bc1685310>",
-        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7f7bc16853a0>",
+        "__init__": "<function DQNPolicy.__init__ at 0x7efe1aa00550>",
+        "_build": "<function DQNPolicy._build at 0x7efe1aa005e0>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7efe1aa00670>",
+        "forward": "<function DQNPolicy.forward at 0x7efe1aa00700>",
+        "_predict": "<function DQNPolicy._predict at 0x7efe1aa00790>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7efe1aa00820>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7efe1aa008b0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f7bc1704700>"
+        "_abc_impl": "<_abc._abc_data object at 0x7efe1aa03940>"
     },
     "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": 1709631678889401888,
-    "learning_rate": 0.0001,
-    "tensorboard_log": null,
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADPmhL36pw4+gBLTu/CPlb1JVMy8dA2ZOwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+    "start_time": 1721095875529543112,
+    "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:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAALPFhL29VhA+jHgyu5fCmL0NPs68z50YPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJCTGD//Mks/mHZvP35yMz3kYQe8v5KSPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
-    "_episode_num": 610,
+    "_episode_num": 537,
     "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 0x7f7bc16db0d0>",
-        "add": "<function ReplayBuffer.add at 0x7f7bc16db160>",
-        "sample": "<function ReplayBuffer.sample at 0x7f7bc16db1f0>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f7bc16db280>",
-        "_maybe_cast_dtype": "<staticmethod object at 0x7f7bc16d2640>",
-        "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f7bc16d6dc0>"
-    },
-    "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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",
@@ -101,7 +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": [],
@@ -109,14 +81,47 @@
         "_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 0x7efe1aa74b80>",
+        "add": "<function ReplayBuffer.add at 0x7efe1aa74c10>",
+        "sample": "<function ReplayBuffer.sample at 0x7efe1aa74ca0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7efe1aa74d30>",
+        "_maybe_cast_dtype": "<staticmethod object at 0x7efe1aaf0e20>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7efe1aa6c600>"
+    },
+    "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:f18d549853c3213be341b35916b696dafabf5b7b83aacf4f7a65b03a20217b5c
-size 45216
+oid sha256:ee2e6269ef9c7cfa6c136dbd258ba2df2419a58f5c1d509b1cdb48df0358a349
+size 558240

dqn-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a6c5b4559a84b25a984d0d95b41c6f173099344303ed48838f11a41016d32c6
-size 44338
+oid sha256:fc892f6197d1f4ebf2172c915d517fe1b2f3dedffb4b2b19e57429fa1bd757c6
+size 557362

dqn-LunarLander-v2/system_info.txt

@@ -1,9 +1,9 @@
-- OS: Linux-6.2.0-1019-azure-x86_64-with-glibc2.36 # 19~22.04.1-Ubuntu SMP Wed Jan 10 22:57:03 UTC 2024
+- OS: Linux-5.15.153.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Mar 29 23:14:13 UTC 2024
 - Python: 3.9.18
 - Stable-Baselines3: 2.1.0
-- PyTorch: 2.2.1+cpu
+- PyTorch: 2.1.0+cpu
 - GPU Enabled: False
-- Numpy: 1.26.4
+- Numpy: 1.26.1
 - Cloudpickle: 3.0.0
 - Gymnasium: 0.29.1
 - OpenAI Gym: 0.26.2

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb107e76cc5f067bb745e1113900d59e6697248fb2b41d5f9054c7698a075a8e
-size 185478
+oid sha256:9c1cb0dc8a7fced2778790830ad58bdf1d508f20ee96b504718925f7f22c63f3
+size 202327

results.json

@@ -1 +1 @@
-{"mean_reward": 87.34864089741605, "std_reward": 35.51083155982755, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-05T09:45:12.924341"}
+{"mean_reward": -188.60461700000002, "std_reward": 65.2025250694205, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-16T07:48:19.238455"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a204f20c4d1fec53f52fd6e4f0f2194e1c5d687ea7a7dc18f9271d09e4da3a7
-size 400
+oid sha256:37352ea717c96308c2cf3e0efee42b7e14e5456d4ec0aefffdb390a581aff955
+size 15688