Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 565.00 +/- 213.27
+      value: 618.00 +/- 169.87
       name: mean_reward
       verified: false
 ---
@@ -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 numan966 -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 numan966 -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 numan966
 ```
@@ -65,9 +70,9 @@ OrderedDict([('batch_size', 64),
              ('exploration_fraction', 0.1),
              ('frame_stack', 4),
              ('gradient_steps', 1),
-             ('learning_rate', 0.0003),
+             ('learning_rate', 0.0002),
              ('learning_starts', 100000),
-             ('n_timesteps', 2000000.0),
+             ('n_timesteps', 4000000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),

args.yml

@@ -54,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 1343356972
+    - 622850569
   - - storage
     - null
   - - study_name

config.yml

@@ -14,11 +14,11 @@
   - - gradient_steps
     - 1
   - - learning_rate
-    - 0.0003
+    - 0.0002
   - - learning_starts
     - 100000
   - - n_timesteps
-    - 2000000.0
+    - 4000000.0
   - - optimize_memory_usage
     - false
   - - policy

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2184cb05563800e8299dbc93a4e42502df95eb708bcc858f7262292a5543cddf
-size 27224809
+oid sha256:d47ab517db617804421d549c3b14657c904e3c1cd805374fe784dd3368749667
+size 27224804

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -1 +1 @@
-1.7.0a11
+1.7.0

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7d2441597b8ebd48e35d41e5944beaad33b0ed07feeed4ce92961d8aec4577a
+oid sha256:2a98d3a3072746ac3fa80d8fdc57f17fb41016734bd0e87b22eb71a4b84c08b9
 size 13505739

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be2837ce666f5096f49cd28046ac3c9a5728245d1fc4150857e401abf590bd6
+oid sha256:23e1c5ebc3dd2dc82e06d04bacb1ae9db3cf1eae430b18afd316e0a5701d32df
 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: 1.7.0a11
-- PyTorch: 1.13.0+cu116
+- OS: Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.8.10
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.1+cu116
 - GPU Enabled: True
 - Numpy: 1.21.6
 - Gym: 0.21.0

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4ec378fee47ad67ff9707cebcb17dd11aeebb9de83663bb5590e654ff65f186
-size 194422
+oid sha256:ad65afe471cb8e3471da591346c2793dc483889c167c6c88817fb0f354bb932f
+size 197802

results.json

@@ -1 +1 @@
-{"mean_reward": 565.0, "std_reward": 213.27212663637036, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-04T19:42:40.427322"}
+{"mean_reward": 618.0, "std_reward": 169.8705389406886, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-20T21:01:26.228474"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba419e1af6cbe0290c2fb6aa6c8f31b0173ffdd5f27f2740f015f4b123d89988
-size 62689
+oid sha256:b71532eff206c3f7d52323ccb45c6a5718626dbcc2e4eb389b1566bee620e5e8
+size 122900