Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -129.09 +/- 98.44
+      value: -264.32 +/- 128.26
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.00025
+'learning_rate': 1.5e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1679401380.7b0e271d7d17.18954.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23209afc6bcdfbd672d48952b62aebe8ced954ebac6ba2f1e09d8a461784a859
+size 229947

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd2d09ce108a051e2e384d5e01bda71dd42ff9b117e243d3d4f61911fd43a9d
+oid sha256:6914b2dc697158cfda58dbb9d6e64da35d8f6bc152301dbee130d7fb443ac37c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -129.08629081725877, "std_reward": 98.44059310272428, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-21T12:15:44.411755"}
+{"env_id": "LunarLander-v2", "mean_reward": -264.32433893266153, "std_reward": 128.25850053142534, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-21T12:24:16.751548"}