Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 17.38 +/- 18.63
+      value: 109.96 +/- 50.36
       name: mean_reward
       verified: false
 ---
@@ -42,7 +42,7 @@ model-index:
 'num_envs': 4
 'num_steps': 2048
 'anneal_lr': False
-'gae': False
+'gae': True
 'gamma': 0.9999
 'gae_lambda': 0.98
 'num_minibatches': 4

logs/events.out.tfevents.1712959892.c5972933496d.3129.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae87ae48161c2370ee61ee611cdf73c2ad7656a97230e053f75e8980519eeb68
+size 1207284

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20497ef1b410cb1c533c1f0fb7ec7927970528e0f42af8e3daf2987e4d858550
+oid sha256:a4af5f371c55081804347e4cbd2bc80039779ae9db48b3743c5e5363b8026ebd
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 17.382341976694644, "std_reward": 18.63255386028582, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-12T19:52:21.260722"}
+{"env_id": "LunarLander-v2", "mean_reward": 109.96438810765797, "std_reward": 50.3625160928574, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-12T23:35:02.144201"}