Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -113.97 +/- 73.68
+      value: 210.74 +/- 101.24
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 10000000
 'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 1024

logs/events.out.tfevents.1680794822.3e2ed397537f.8272.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9ab99ea4b3c63716cf324092b2006d4bf582833550d5f755b54b28b0bd6637
+size 5435363

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b85a92cbfc327374671604a51894b2ff30e8a3e97df009e23e0bfbf66e4122e
+oid sha256:0e60c0dd0bc0b77da4c1a440e5e0902c0f16a80ce91c63ab19916663819f047d
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -113.96514089131817, "std_reward": 73.6806298435624, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-06T15:23:49.417796"}
+{"env_id": "LunarLander-v2", "mean_reward": 210.74351645645635, "std_reward": 101.23705847809467, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-06T18:08:31.996668"}