Initial Commit - Only for test

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 280.07 +/- 12.93
+      value: 278.25 +/- 19.34
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2-linker-v1_2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81e9cf61a17668263a878cafc2e42a0501917f9fb4b1f0ae9f493a444b82795d
+oid sha256:8a2f7ca27af48e18b98e34a0b6e939fc1d7709b7f0ec761e42e4ce2b4369ed5b
 size 144392

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26154e5d22519d53c608fca67dbda6929a0e4e62d6bf23823190e45235bfa4f2
-size 206832
+oid sha256:d736f24ebc75498cb12ce60f81f0065604ce1e914b42141d1ab6b83aa50d771e
+size 212861

results.json

@@ -1 +1 @@
-{"mean_reward": 280.06990819203867, "std_reward": 12.93103281815856, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-09T21:39:09.957297"}
+{"mean_reward": 278.25192633639324, "std_reward": 19.337104317280033, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-09T21:43:48.108291"}