Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -167.17 +/- 98.82
+      value: -128.72 +/- 69.27
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1700035040.d492094d352d.5846.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e7d4e12ddfbc7cf64948ff2af2e1a23073a5102628345c86efda86ede23331
+size 221326

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6924baa5dd037fce235630a196da2d3b4ab3db5b2a406adc766bdd0487a7d923
+oid sha256:bf4a7fde3320b1226867f811244d8c33574eca701ec88ceee90bda5c8724f5d8
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -167.1739260977672, "std_reward": 98.82292953944071, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-15T07:56:54.131838"}
+{"env_id": "LunarLander-v2", "mean_reward": -128.72319492004266, "std_reward": 69.27314905640965, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-15T07:58:41.561212"}