Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -168.58 +/- 76.20
+      value: -100.21 +/- 67.79
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'f': '/root/.local/share/jupyter/runtime/kernel-034b7df4-145b-4db4-9d09-b6d875ced33d.json'
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.00024
+'learning_rate': 0.0004
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1691895181.4c5d58e91a6c.225.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99437276d69c9e431029860ac729bda976772fef56516a5734a63067c3fc2471
+size 212845

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a717a7b46d613afca5e9a9eecab969dba1168a8005833a002725683fbc2137f3
+oid sha256:8d8698b202d5caf285d4f840fd837056492884e0e71ffb1e6267c622c2e81452
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -168.5756999427687, "std_reward": 76.20170511961085, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:52:39.589292"}
+{"env_id": "LunarLander-v2", "mean_reward": -100.2069420919785, "std_reward": 67.7877861350826, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:54:36.813636"}