Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -131.68 +/- 83.94
+      value: 60.26 +/- 69.09
       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': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1680989257.bi-16.prod.env.758219.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aa003e89ee65cea025f83e547d1954c0a8142d2c544e6a514b2f3cf216cbbbc
+size 673965

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08d3ffda7f890ca9715ac190f20b7c3a8ed8de6d181ef66b5819ab4931294e6b
+oid sha256:4ba791dc7331097b7e18d251d984e1b5de9ba065fb3fa5b57349f0c975b98b8c
 size 42817

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -131.6786513627094, "std_reward": 83.94449782838775, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-08T21:24:19.361552"}
+{"env_id": "LunarLander-v2", "mean_reward": 60.26427900348342, "std_reward": 69.09237253712162, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-08T21:37:40.927702"}