Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -157.31 +/- 149.85
+      value: 11.52 +/- 57.92
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 2000000
 'learning_rate': 0.00025
 'num_envs': 16
 'num_steps': 1024

logs/events.out.tfevents.1676774877.5e7fcccfc678.10707.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d2fc51843cb33ffad8981c268f4341eb3533c70ff63066dcd3a0e5d2b9da60
+size 1205508

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c6444902951740fb78da7b5b51fb5ccd48eb21ee467064a2e5ff121b1655243
+oid sha256:9b2e7c7dea85ca934dc40c147fec2d06f54d89ad450deebfcdc7a53c820753a3
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -157.3052475209271, "std_reward": 149.851983031017, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T02:40:00.886251"}
+{"env_id": "LunarLander-v2", "mean_reward": 11.516702013573903, "std_reward": 57.919773365779754, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T03:13:33.369138"}