Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 148.13 +/- 119.08
+      value: 151.12 +/- 130.54
       name: mean_reward
       verified: false
 ---
@@ -33,7 +33,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'learning_rate': 0.01
 'seed': 1
-'total_timesteps': 100000
+'total_timesteps': 500000
 'torch_deterministic': True
 'cuda': True
 'record_video': None

logs/events.out.tfevents.1686529749.4c7cbfaa41ac.56291.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a537b853e537271c9896601daa147f72084841e5c13802f89964981121b1ddd8
+size 613814

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfd71a0732a44566a5e8b62fce8b140809908b6d4249e3ca059f9c1dc06472cb
+oid sha256:09ec321b3debc5bdafe15b8a4cb25af768c58463ef53dc4f0975fc61f73e96c3
 size 6949

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 148.1259109599605, "std_reward": 119.08399632789636, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T00:27:53.692280"}
+{"env_id": "LunarLander-v2", "mean_reward": 151.11725797317555, "std_reward": 130.54094318231103, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T00:43:22.915927"}