Initial commit

README.md

@@ -0,0 +1,86 @@
+---
+library_name: stable-baselines3
+tags:
+- SpaceInvadersNoFrameskip-v4
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: SpaceInvadersNoFrameskip-v4
+      type: SpaceInvadersNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 265.50 +/- 29.11
+      name: mean_reward
+      verified: false
+---
+
+# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
+This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
+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 SpaceInvadersNoFrameskip-v4 -orga Fremonta -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -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 SpaceInvadersNoFrameskip-v4 -orga Fremonta -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Fremonta
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 32),
+             ('buffer_size', 100000),
+             ('env_wrapper',
+              ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
+             ('exploration_final_eps', 0.01),
+             ('exploration_fraction', 0.1),
+             ('frame_stack', 4),
+             ('gradient_steps', 1),
+             ('learning_rate', 0.0001),
+             ('learning_starts', 100000),
+             ('n_timesteps', 1000.0),
+             ('optimize_memory_usage', False),
+             ('policy', 'CnnPolicy'),
+             ('target_update_interval', 1000),
+             ('train_freq', 4),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a9d92452401a31a97943425137b3f92d67f7386daf1f27db1d90ccd15654bc
+oid sha256:70ce880df0ca35fdc3815092447b6aeee52b6fd05c3d3c0aafee70d6d0bcb3ee
 size 13710927

dqn-SpaceInvadersNoFrameskip-v4/data

@@ -4,9 +4,9 @@
         ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCUNublBvbGljeZSTlC4=",
         "__module__": "stable_baselines3.dqn.policies",
         "__doc__": "\n    Policy class for DQN when using images as input.\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 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 CnnPolicy.__init__ at 0x7ff298eadc60>",
+        "__init__": "<function CnnPolicy.__init__ at 0x7fe6c9df9e10>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7ff298ea7f00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fe6c9e0c480>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -84,13 +84,13 @@
         "__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 0x7ff2991b0ee0>",
-        "add": "<function ReplayBuffer.add at 0x7ff2991b0f70>",
-        "sample": "<function ReplayBuffer.sample at 0x7ff2991b1000>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7ff2991b1090>",
-        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7ff2991b1120>)>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7fe6ca0f9090>",
+        "add": "<function ReplayBuffer.add at 0x7fe6ca0f9120>",
+        "sample": "<function ReplayBuffer.sample at 0x7fe6ca0f91b0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fe6ca0f9240>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fe6ca0f92d0>)>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7ff299336500>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fe6ca267fc0>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f901fa8c56c59ed38b0824b3441dc8fe24c72d3d365bd6838a2956249c5da5
+size 268225

results.json

@@ -1 +1 @@
-{"mean_reward": 265.5, "std_reward": 29.107559155655768, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-17T00:42:34.380796"}
+{"mean_reward": 265.5, "std_reward": 29.107559155655768, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-17T00:47:59.102412"}