Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -149.55 +/- 89.84
+      value: 62.98 +/- 95.87
       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.1678906310.c453447ec42b.3837.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e71a7c110d48f3d9eef6f925e38248dd3ed4c0677195de57b37d4d983bd453e
+size 659816

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:a9f46f0c7b70f362e72eed22c3293e3d84fecfb7f3a67337d95096ecff1763a0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -149.55165189954022, "std_reward": 89.84168535124051, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-15T18:50:57.015141"}
+{"env_id": "LunarLander-v2", "mean_reward": 62.97647964836936, "std_reward": 95.86751761717562, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-15T19:05:49.102284"}