Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -147.07 +/- 69.77
+      value: -46.82 +/- 64.12
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1712792648.a5905334897b.4331.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78ebd83c34b5873f238b8b10e1a5e83450ddaac2cc16ec9a12fef8e1b53e757
+size 663571

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51141f29a5fd60d9f7a96a70a1e185897fcb1c4838b12131a7276001db13c08
+oid sha256:f6ca04aff66f64822aba97da008791460d2a13e5294599c0e9a57325ed9eacdb
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -147.0656790511522, "std_reward": 69.77486517774335, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-10T23:43:42.468434"}
+{"env_id": "LunarLander-v2", "mean_reward": -46.82464874786403, "std_reward": 64.12046138424112, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-11T00:00:31.078610"}