Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -120.07 +/- 40.47
+      value: -23.72 +/- 113.11
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 80000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1693460330.a8861407b5b2.3844.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ce04b6ca2a9040afaf046b62637ad68609c497984d6a19c0b3cf8986837162
+size 675248

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb65e985346994f8ee8a7338bb55c48b034835ebd61bf267de94d9e31f58d07
+oid sha256:95d2db815a33646e84e478628a4da4f156c95480a7b55276eebdc219ec4fcd18
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -120.06644217500875, "std_reward": 40.47137446285766, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-31T05:37:56.439004"}
+{"env_id": "LunarLander-v2", "mean_reward": -23.71871646792318, "std_reward": 113.11070328403933, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-31T05:53:59.874270"}