Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -132.01 +/- 102.58
+      value: -95.54 +/- 59.68
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1705167937.8dc59aebe1a6.5342.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e38a348b9089bdbf4b80fec9b29ead44a151080a834d29c8c07da1e4e8d0629
+size 221321

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:bf4a7fde3320b1226867f811244d8c33574eca701ec88ceee90bda5c8724f5d8
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -132.0125422888121, "std_reward": 102.58287654219058, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-13T17:41:36.499051"}
+{"env_id": "LunarLander-v2", "mean_reward": -95.53784872767316, "std_reward": 59.68075654080956, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-13T17:46:57.040191"}