Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 413.50 +/- 197.00
+      value: 578.00 +/- 133.61
       name: mean_reward
       verified: false
 ---
@@ -62,21 +62,21 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
 
 ## Hyperparameters
 ```python
-OrderedDict([('batch_size', 256),
-             ('buffer_size', 100000),
+OrderedDict([('batch_size', 32),
+             ('buffer_size', 150000),
              ('env_wrapper',
               ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
-             ('exploration_final_eps', 0.01),
-             ('exploration_fraction', 0.1),
+             ('exploration_final_eps', 0.010499732933570786),
+             ('exploration_fraction', 0.3847312822999899),
              ('frame_stack', 4),
              ('gradient_steps', 1),
-             ('learning_rate', 0.00025),
-             ('learning_starts', 100000),
+             ('learning_rate', 0.0005104911831540507),
+             ('learning_starts', 150000),
              ('n_timesteps', 1000000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
-             ('target_update_interval', 1000),
-             ('train_freq', 4),
+             ('target_update_interval', 3418),
+             ('train_freq', 7),
              ('normalize', False)])
 ```
 

args.yml

@@ -56,7 +56,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 851308805
+    - 2452322081
   - - storage
     - null
   - - study_name

config.yml

@@ -1,22 +1,22 @@
 !!python/object/apply:collections.OrderedDict
 - - - batch_size
-    - 256
+    - 32
   - - buffer_size
-    - 100000
+    - 150000
   - - env_wrapper
     - - stable_baselines3.common.atari_wrappers.AtariWrapper
   - - exploration_final_eps
-    - 0.01
+    - 0.010499732933570786
   - - exploration_fraction
-    - 0.1
+    - 0.3847312822999899
   - - frame_stack
     - 4
   - - gradient_steps
     - 1
   - - learning_rate
-    - 0.00025
+    - 0.0005104911831540507
   - - learning_starts
-    - 100000
+    - 150000
   - - n_timesteps
     - 1000000.0
   - - optimize_memory_usage
@@ -24,6 +24,6 @@
   - - policy
     - CnnPolicy
   - - target_update_interval
-    - 1000
+    - 3418
   - - train_freq
-    - 4
+    - 7

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0437bfbf0f894d41616dd1683fa20d91e97b9dd15aaa096beb75b9045faccee
-size 27220729
+oid sha256:c5be37d74918db71dd8fb3e24fd5585468b88ab229dd9d97754925c99eef74a9
+size 27220794

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da81ca803e47a5a9c2e4e5a6576b1ec62b9fed60e30365b9ff465077fb6ce91f
+oid sha256:afc45debfc2ebddadee0f00b1300e157c794e90fe7e827e3537efd482785ed43
 size 13506172

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dbb9a0d78bea6bfdbd9ec052b977107883c4c1725b07859e7407ad285109948
+oid sha256:6afbe30a3673007e0111b80e9b60f5dd8881cc537a41f33bfb19222943820476
 size 13505370

results.json

@@ -1 +1 @@
-{"mean_reward": 413.5, "std_reward": 197.0031725632864, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-02T22:59:33.244640"}
+{"mean_reward": 578.0, "std_reward": 133.6076345124035, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-03T23:13:22.440239"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be6650709136fb31a7bb993c1e83314df31454dcc1218a96eb7395be4ca83b05
-size 40079
+oid sha256:daecd60378ae84b7387bb087e56a06c2a70226b6c6496df798655d3bb1e53899
+size 39648