Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 312.50 +/- 144.78
+      value: 329.00 +/- 157.97
       name: mean_reward
       verified: false
 ---
@@ -72,8 +72,8 @@ OrderedDict([('batch_size', 32),
              ('frame_stack', 4),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
-             ('learning_starts', 100000),
-             ('n_timesteps', 200000),
+             ('learning_starts', 1000000.0),
+             ('n_timesteps', 100000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),

args.yml

@@ -56,7 +56,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 2199309905
+    - 1378870051
   - - storage
     - null
   - - study_name

config.yml

@@ -16,9 +16,9 @@
   - - learning_rate
     - 0.0001
   - - learning_starts
-    - 100000
+    - 1000000.0
   - - n_timesteps
-    - 200000
+    - 100000.0
   - - optimize_memory_usage
     - false
   - - policy

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:089acfac33e91f7e7174f1f4540d78411ceedca62008829ac24bae44d8a612c2
-size 27220508
+oid sha256:325ba918b2ca996fb431a14d4c3c3ad857e54aca19d83fb983df3a69670359c7
+size 13715774

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e587151dac428680d7427b9f55cc443aaa7475d5ad12b7cb49914699c8825733
-size 13505852
+oid sha256:215ea7d8898faa9284464c7109532cf36390d330fccab8d77eeba20628a32876
+size 1120

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4029391efe45e858ca50f1a0545af2fde0f2be7420de69236738efe8bc9112ee
+oid sha256:ba79915493f9d60507c9a034970eb33e4a5d2f2521088da0b464ea81dbde3023
 size 13505178

results.json

@@ -1 +1 @@
-{"mean_reward": 312.5, "std_reward": 144.78000552562497, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-02T20:00:27.053577"}
+{"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-04T21:52:37.190023"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ce750b34959c7535b44a721339232d94d886ac8a6a37dc54f600abde377f5c
-size 9711
+oid sha256:7e729a0124dc8e952e63678a26c52da9e2048fb3c9c7c013ef50c08d358bb754
+size 5937