Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -47.15 +/- 46.02
+      value: -42.32 +/- 38.75
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 150000
+'total_timesteps': 300000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1696278648.038f7278529f.8802.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2b928e0284419363f9da0db8db4d615987e892e29f47b58e03857377490590
+size 427495

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39bad5aad3ef043732732a6b93a3799d7215121a5aeed6da2ba11e7403434a24
+oid sha256:ead806b289e5cd9863afb529e2d3d9b7d4cd26761d191d67ceb55b4a10c8e594
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -47.14700270641367, "std_reward": 46.02016177758704, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-02T20:29:57.273328"}
+{"env_id": "LunarLander-v2", "mean_reward": -42.31997145505096, "std_reward": 38.74793098755609, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-02T20:39:14.430636"}