Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 171.00 +/- 32.92
+      value: 457.50 +/- 157.18
       name: mean_reward
       verified: false
 ---
@@ -58,16 +58,16 @@ 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', 150000),
              ('env_wrapper',
               ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
              ('exploration_final_eps', 0.01),
-             ('exploration_fraction', 0.1),
-             ('frame_stack', 4),
+             ('exploration_fraction', 0.15),
+             ('frame_stack', 3),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
-             ('n_timesteps', 1000000.0),
+             ('n_timesteps', 1200000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),

args.yml

@@ -1,6 +1,8 @@
 !!python/object/apply:collections.OrderedDict
 - - - algo
     - dqn
+  - - conf_file
+    - null
   - - device
     - auto
   - - env
@@ -52,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 2176844926
+    - 184500454
   - - storage
     - null
   - - study_name

config.yml

@@ -2,15 +2,15 @@
 - - - batch_size
     - 32
   - - buffer_size
-    - 100000
+    - 150000
   - - env_wrapper
     - - stable_baselines3.common.atari_wrappers.AtariWrapper
   - - exploration_final_eps
     - 0.01
   - - exploration_fraction
-    - 0.1
+    - 0.15
   - - frame_stack
-    - 4
+    - 3
   - - gradient_steps
     - 1
   - - learning_rate
@@ -18,7 +18,7 @@
   - - learning_starts
     - 100000
   - - n_timesteps
-    - 1000000.0
+    - 1200000.0
   - - optimize_memory_usage
     - false
   - - policy

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5cd8be34a3f3427f5be4415acf97b039ae924bb2f315a1deb2272efbb98cca7
-size 27224959
+oid sha256:f0dfa399c7837af47c4513692d132d6183e1c88610e8c527eb8c1bfa50ae4a16
+size 27144077

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beba3d931a1b4525c54da44efe65a28d06c565815bae5a753aaa7246aa320f0f
-size 13505739
+oid sha256:1f53aaf5d0ee3ab9baba5d69fd3ad6ba136c1b5a49904cb521f7899d75561b6a
+size 13489355

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:550edc451702fe2adcb97dd077569118dd721d6b482f894e75930c087f7319d6
-size 13504937
+oid sha256:703e2c80fd154688015d3d57d846cb38d417b5d4c933cffe9e9e12c4d4c1558b
+size 13488553

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -1,7 +1,7 @@
-OS: Linux-5.10.133+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022
-Python: 3.7.15
+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: 1.6.2
-PyTorch: 1.12.1+cu113
+PyTorch: 1.13.0+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:f89b24ca84a29ab210f6488d87d909d392ae823c1b3af7956137e3e302aaf735
-size 243904
+oid sha256:10940277f02f144afa99a6332ba7587a6cc247604e860e40cddca02269ae407a
+size 199091

results.json

@@ -1 +1 @@
-{"mean_reward": 171.0, "std_reward": 32.92415526630866, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-11-12T05:00:16.212793"}
+{"mean_reward": 457.5, "std_reward": 157.18221909618148, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-09T07:29:37.576281"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f14088058ac066596a74c81e106cb52eb1bf56934eaeebc54c737ebe8cf4b8
-size 9393
+oid sha256:8016b282b5ddb1f1e9348f0c7cc1485c229ca87f4868ddda7029367b4bcc468d
+size 43228