Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -128.23 +/- 72.54
+      value: -17.67 +/- 117.76
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': True
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1676568633.a72fabec5a78.5046.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1ab3de97cf1cfb525cbc0176500102ea6c812c10ea3c485d808a22d965c937
+size 1253246

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0762c60b8952f57601a85c2d5d3d6f6e862f4cc07ba530b06e3bd7b2d806a2a3
+oid sha256:ab15a16b18b87bf962ef37e699d27733152d033658070d279c74e1eede715b34
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -128.23019915308976, "std_reward": 72.53795879595121, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T17:27:01.528577"}
+{"env_id": "LunarLander-v2", "mean_reward": -17.671538775258963, "std_reward": 117.76015621919962, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T18:04:41.889779"}