Initial commit

README.md

@@ -8,16 +8,17 @@ tags:
 model-index:
 - name: DQN
   results:
-  - metrics:
-    - type: mean_reward
-      value: 1092.00 +/- 250.80
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: SpaceInvadersNoFrameskip-v4
       type: SpaceInvadersNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 711.50 +/- 293.52
+      name: mean_reward
+      verified: false
 ---
 
 # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
@@ -35,17 +36,28 @@ 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 utils.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga micheljperez -f logs/
-python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga micheljperez -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 micheljperez -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 
 ## Training (with the RL Zoo)
 ```
-python train.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
+python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
 # Upload the model and generate video (when possible)
-python -m utils.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga micheljperez
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga micheljperez
 ```
 
 ## Hyperparameters
@@ -55,15 +67,20 @@ OrderedDict([('batch_size', 32),
              ('env_wrapper',
               ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
              ('exploration_final_eps', 0.01),
-             ('exploration_fraction', 0.025),
+             ('exploration_fraction', 0.1),
              ('frame_stack', 4),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
              ('n_timesteps', 10000000),
-             ('optimize_memory_usage', True),
+             ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),
              ('train_freq', 4),
              ('normalize', False)])
 ```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -1,6 +1,8 @@
 !!python/object/apply:collections.OrderedDict
 - - - algo
     - dqn
+  - - conf_file
+    - dqn.yml
   - - device
     - auto
   - - env
@@ -41,6 +43,8 @@
     - null
   - - optimize_hyperparameters
     - false
+  - - progress
+    - false
   - - pruner
     - median
   - - sampler
@@ -50,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 1081596659
+    - 3252750409
   - - storage
     - null
   - - study_name
@@ -73,3 +77,5 @@
     - null
   - - wandb_project_name
     - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -8,7 +8,7 @@
   - - exploration_final_eps
     - 0.01
   - - exploration_fraction
-    - 0.025
+    - 0.1
   - - frame_stack
     - 4
   - - gradient_steps
@@ -20,7 +20,7 @@
   - - n_timesteps
     - 10000000
   - - optimize_memory_usage
-    - true
+    - false
   - - policy
     - CnnPolicy
   - - target_update_interval

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7beed6b59a11de91972dad8df92e19379adadc80cb3f5f67108646298a36b7cd
-size 27221974
+oid sha256:31aa5df43a882008160bc234fd27a404f4d940852dabaeb5f35c74de576da124
+size 27219638

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -1 +1 @@
-1.5.1a8
+2.1.0

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f11405df4f68a2f5874d6a8a7a9f04b933c524697ad0eea7c8f4dcf326ce809
-size 13502953
+oid sha256:b58c1eb88e0039813f6322f3adf50772c9708208fa4c043f986d836dc3c28474
+size 13505852

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a1c123023c53acec1377469a02906be02824736fc9a39d82c206fb399518f4
-size 13504745
+oid sha256:8b28b4d161cfe6e912af427bc1a6abaeb9572a9a3f2cde86f55c06f3aa09320d
+size 13505178

dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
-size 431
+oid sha256:ebdad4b9cfe9cd22a3abadb5623bf7bb1f6eb2e408740245eb3f2044b0adc018
+size 864

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -1,7 +1,9 @@
-OS: macOS-12.4-arm64-arm-64bit Darwin Kernel Version 21.5.0: Tue Apr 26 21:08:37 PDT 2022; root:xnu-8020.121.3~4/RELEASE_ARM64_T6000
-Python: 3.8.9
-Stable-Baselines3: 1.5.1a8
-PyTorch: 1.11.0
-GPU Enabled: False
-Numpy: 1.23.0
-Gym: 0.21.0
+- OS: macOS-13.6-arm64-arm-64bit Darwin Kernel Version 22.6.0: Fri Sep 15 13:41:28 PDT 2023; root:xnu-8796.141.3.700.8~1/RELEASE_ARM64_T6000
+- Python: 3.8.10
+- Stable-Baselines3: 2.1.0
+- PyTorch: 2.1.0
+- GPU Enabled: False
+- Numpy: 1.24.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.26.2

env_kwargs.yml

@@ -1 +1 @@
-{}
+render_mode: rgb_array

results.json

@@ -1 +1 @@
-{"mean_reward": 1092.0, "std_reward": 250.80071770232237, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-25T20:27:42.617325"}
+{"mean_reward": 711.5, "std_reward": 293.52214567217925, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-10-27T09:23:02.380003"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67a8c8e46747d034c6e21718531a183efb4b4ac9090e6d3f1f50bf8f38528f2d
-size 272785
+oid sha256:fd0fad125447e8300539683ba028638571f438110ef7260a07ed27551ffa5977
+size 277427