Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 153.00 +/- 26.94
+      value: 240.50 +/- 82.75
       name: mean_reward
       verified: false
 ---
@@ -71,8 +71,8 @@ OrderedDict([('batch_size', 32),
              ('frame_stack', 4),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
-             ('learning_starts', 1000),
-             ('n_timesteps', 100000.0),
+             ('learning_starts', 100000),
+             ('n_timesteps', 10000000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),

args.yml

@@ -54,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 3574483888
+    - 2021896475
   - - storage
     - null
   - - study_name

config.yml

@@ -16,9 +16,9 @@
   - - learning_rate
     - 0.0001
   - - learning_starts
-    - 1000
+    - 100000
   - - n_timesteps
-    - 100000.0
+    - 10000000.0
   - - optimize_memory_usage
     - false
   - - policy

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81f95e14d364dffd2c6eb45bb8b057de29005cd84c774bd3c6d484347b4ae8d
-size 27218315
+oid sha256:e98beacf5633941ec764707b0ac932adf4cc8ed9e9dfcdbca163666fe155775e
+size 27218410

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc181de6978776263c4e42b340ee49624e81ea5f8c919416489b5a70537f521b
+oid sha256:60bb4f77ab4742059b131eb138ccd14bf8a4d45f9a22d2772d3d368773a331b6
 size 13505739

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e9b3b36166a013e658c1865c0e23a44fb0a3b7ac2fdf4251572b6867e4bd3f9
+oid sha256:7a0b495cdc7c36ad41c22372fbf85c9e9f4b7164a9a826039bfa123d5605a63a
 size 13504937

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f043da3698784e6de2b1d1afd431b3eecbeec9d93069cf0c7affa17237dbc59
-size 266533
+oid sha256:c620f0f1bc96c5afc529051074859115c8c3c8064742017fde17fd71e1095295
+size 262665

results.json

@@ -1 +1 @@
-{"mean_reward": 153.0, "std_reward": 26.94438717061496, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-06-16T10:05:04.064815"}
+{"mean_reward": 240.5, "std_reward": 82.74811176093385, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-06-16T10:06:55.320379"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af96319c30a0ab293000544986b6adce2babd3281c32dc4b20ca4af61695f64
-size 3429
+oid sha256:4db8225488bbf9abc29522b1c8ff77614e649bbd0220d2bceed3c559c3df2626
+size 22602