Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -117.96 +/- 96.83
+      value: -109.81 +/- 52.14
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': True
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 1000000
 'learning_rate': 2e-05
 'num_envs': 4
 'num_steps': 256

logs/events.out.tfevents.1678361263.de9c9160a6a5.45484.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc1495ab8283b42e220f37dd9bd75313f862f48f8ea087727805773fb13396d
+size 1636321

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fafed7c99cfae4cb09c6dfb7f799de17a117108938fca897216cd11dbfab4f
+oid sha256:02921246f1dce10e35dd0c1451fc703dff4a95ade819813268aec67c268e5929
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -117.95584882194075, "std_reward": 96.8333968536081, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-09T11:13:15.113139"}
+{"env_id": "LunarLander-v2", "mean_reward": -109.80916397073432, "std_reward": 52.13748526413528, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-09T11:42:15.838018"}