Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -61.51 +/- 63.95
+      value: 88.76 +/- 131.17
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'repo_id': 'ntrant7/ppo-LunarLander-v2'
 'env_id': 'LunarLander-v2'
 'total_timesteps': 200000
-'learning_rate': 0.00025
+'learning_rate': 0.003
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1682861687.73e30408940d.12685.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffcb180c42fa3494df909fcf164219a9c3dbceda464e2c0f01094b76eedcf1f4
+size 264495

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f535a1b6e2cb3d7ae16b9eaf1f7b1788c698bb91db99c0c95a696a1a9353705c
+oid sha256:778a66f77212d695c9724318a2cd1a851d99aada7175c607cda494bcb5da18c1
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -61.51206049200287, "std_reward": 63.9517986500426, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T13:32:11.317458"}
+{"env_id": "LunarLander-v2", "mean_reward": 88.75666232495766, "std_reward": 131.16701859141952, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T13:39:39.830775"}