Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -118.56 +/- 61.96
+      value: -21.33 +/- 99.79
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1710253811.28d9d214646f.17780.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958b19088b334132796f65080ad7e212a7365800e557b6e4f460aeb3d275625e
+size 1255280

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d7dd5e3988bbef80f64243ce6cc4003af98cb92a17fa58a0c9c43a24eda687
+oid sha256:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -118.55663694587076, "std_reward": 61.96064426635911, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-12T14:17:45.700312"}
+{"env_id": "LunarLander-v2", "mean_reward": -21.329722121677865, "std_reward": 99.78723898164773, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-12T14:56:50.973649"}