Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -57.11 +/- 63.15
+      value: 31.27 +/- 115.10
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
-'learning_rate': 0.0004
+'total_timesteps': 1000000
+'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1727443034.1e2f3d257e25.10125.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea4cce95d3bb45d730ab2a431afd7ac7b2838084832063fd5b8f317e969c161
+size 1255271

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb69aef8884fbabb01617be655347325f2c0125aaeaf5467d7f863d1c1ee17e
+oid sha256:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -57.10781985180536, "std_reward": 63.15254573152223, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-27T13:03:58.993174"}
+{"env_id": "LunarLander-v2", "mean_reward": 31.27017484900832, "std_reward": 115.09811070185707, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-27T13:45:28.214268"}