Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -114.71 +/- 33.02
+      value: -60.84 +/- 133.85
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 5e-05
+'learning_rate': 0.005
 'num_envs': 4
 'num_steps': 1024
 'anneal_lr': True

logs/events.out.tfevents.1691962713.4fbe864f7f94.2652.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f3d800ed1b10fd087880241e3a6d7a540f675c2244cbbed2178008b1405f15f
+size 67783

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2718aa8d9e9f705a9be86dc0148c82a8aaec14ab49842beb2d6abe59d7a2f9ab
+oid sha256:971994662d740bcde6902c6c3a2530b109c4948f0b26decf1be687f47619c3fa
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -114.71417016647395, "std_reward": 33.01933499869112, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T21:37:42.030060"}
+{"env_id": "LunarLander-v2", "mean_reward": -60.839662051952885, "std_reward": 133.84627785328516, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T21:41:07.004896"}