Initial commit

README.md

@@ -36,21 +36,26 @@ 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 sartajbhuvaji -f logs/
-python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4  -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 sartajbhuvaji -f logs/
-rl_zoo3 enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -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 rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga sartajbhuvaji
 ```
@@ -58,16 +63,16 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
 ## Hyperparameters
 ```python
 OrderedDict([('batch_size', 32),
-             ('buffer_size', 100000),
+             ('buffer_size', 10000),
              ('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_rate', 0.001),
              ('learning_starts', 100000),
-             ('n_timesteps', 100000.0),
+             ('n_timesteps', 1000000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),

args.yml

@@ -54,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 3547615024
+    - 1011172713
   - - storage
     - null
   - - study_name
@@ -77,5 +77,5 @@
     - null
   - - wandb_project_name
     - sb3
-  - - yaml_file
-    - null
+  - - wandb_tags
+    - []

config.yml

@@ -2,7 +2,7 @@
 - - - batch_size
     - 32
   - - buffer_size
-    - 100000
+    - 10000
   - - env_wrapper
     - - stable_baselines3.common.atari_wrappers.AtariWrapper
   - - exploration_final_eps
@@ -14,11 +14,11 @@
   - - gradient_steps
     - 1
   - - learning_rate
-    - 0.0001
+    - 0.001
   - - learning_starts
     - 100000
   - - n_timesteps
-    - 100000.0
+    - 1000000.0
   - - optimize_memory_usage
     - false
   - - policy

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92f07cba323794a6d01be749c5c6ab6be9ceda189d0f1a06ecb6d36ce911411b
-size 13719733
+oid sha256:cccc7f6dedddce34f8c4c8c42ca46a90358c8f7be81b4b726768377282a20eba
+size 27224843

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -1 +1 @@
-1.7.0a10
+1.8.0

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e067afe9912f3dd1b7925918b8cbe439229f6008e572c9c7e431ae731419f1
-size 687
+oid sha256:ae851940d8f915dde255898277b6c7ece90f03369b5e6d27c6767e29b861c949
+size 13505739

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7851f940c80b90370bca8b4ec3b2f1218b9e63793e0e506197d288a36f9d5c7d
+oid sha256:a3550b8a7c5fe008b85e823679c0293256ccd83be4803c8706116a81353471a1
 size 13504937

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -1,7 +1,7 @@
-OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
-Python: 3.8.16
-Stable-Baselines3: 1.7.0a10
-PyTorch: 1.13.0+cu116
-GPU Enabled: True
-Numpy: 1.21.6
-Gym: 0.21.0
+- OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.9.16
+- Stable-Baselines3: 1.8.0
+- PyTorch: 2.0.0+cu118
+- GPU Enabled: True
+- Numpy: 1.22.4
+- Gym: 0.21.0

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4f1d23d7804882340d6f0dd57f9d6585261a116cde3d1cac98de13ebf75499a
-size 262996
+oid sha256:caa6a1f28e357785d754b2769d1539f69db8d8cc9b953475f14f2f15f30761f4
+size 263235

results.json

@@ -1 +1 @@
-{"mean_reward": 275.5, "std_reward": 83.07978093375065, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-26T19:20:32.967136"}
+{"mean_reward": 275.5, "std_reward": 83.07978093375065, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-08T17:40:48.028794"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:897eba56504209227b810388a9793543c824bf8cd6c40f436fae821ac603519f
-size 5788
+oid sha256:e7453e356c585ab6a1f9897e30aed0c47b7801f08aea06390451c3c6413fae78
+size 40975