Initial commit

.gitattributes

@@ -32,3 +32,4 @@ 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 +1,81 @@
+---
+library_name: stable-baselines3
+tags:
+- MsPacmanNoFrameskip-v4
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MsPacmanNoFrameskip-v4
+      type: MsPacmanNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 2709.00 +/- 358.62
+      name: mean_reward
+      verified: false
+---
+
+# **DQN** Agent playing **MsPacmanNoFrameskip-v4**
+This is a trained model of a **DQN** agent playing **MsPacmanNoFrameskip-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 MsPacmanNoFrameskip-v4 -orga ljicvedera -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env MsPacmanNoFrameskip-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 MsPacmanNoFrameskip-v4 -orga ljicvedera -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env MsPacmanNoFrameskip-v4  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo dqn --env MsPacmanNoFrameskip-v4 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo dqn --env MsPacmanNoFrameskip-v4 -f logs/ -orga ljicvedera
+```
+
+## 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', 10000000.0),
+             ('optimize_memory_usage', True),
+             ('policy', 'CnnPolicy'),
+             ('target_update_interval', 1000),
+             ('train_freq', 4),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,73 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - device
+    - auto
+  - - env
+    - MsPacmanNoFrameskip-v4
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - 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
+    - 1809550766
+  - - 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 +1,29 @@
+!!python/object/apply:collections.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
+    - 10000000.0
+  - - optimize_memory_usage
+    - true
+  - - policy
+    - CnnPolicy
+  - - target_update_interval
+    - 1000
+  - - train_freq
+    - 4

dqn-MsPacmanNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb9c071d6b7da7c0c465f18e4b556a190bcc97eb00743842978d07d0098e347
+size 27247841

dqn-MsPacmanNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+1.7.0

dqn-MsPacmanNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb0ca88af4bcf066150c8b6e5b646357c5ad47e5f24e866a76c254f74885b3fd
+size 13517707

dqn-MsPacmanNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc19806264d7899396d4aa9a875b806ff4f74bbbb39ff50de78fe28004d0137d
+size 13517033

dqn-MsPacmanNoFrameskip-v4/pytorch_variables.pth

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

dqn-MsPacmanNoFrameskip-v4/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.8.16
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.0+cu116
+- GPU Enabled: False
+- 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 sha256:575b3c8583e2f926209883d526b743533015cc5a8e9fd11ae6bed2bba6cbd02d
+size 239642

results.json

@@ -0,0 +1 @@
+{"mean_reward": 2709.0, "std_reward": 358.62096982747676, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-10T22:14:43.343869"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731586c61aefc1ed7ed7a69d4bcbd0f1803f405f2cac52cac7d449e29590d92c
+size 309818