Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -127.28 +/- 70.86
+      value: -113.79 +/- 36.26
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 50000
+'total_timesteps': 100000
 'torch_deterministic': True
 'cuda': True
 'track': False

logs/events.out.tfevents.1685269622.2901d87a9fc9.8530.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c850dabc4e5196131fccbf3f1089a04fc5b98448cdf7ae9e409cb4c02d5ed7
+size 220828

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bdfe2385f7656fdf6095e0c4e9b5a5e5c8e334304b7b4314f4246f2e68290ef
+oid sha256:47e73f76532fa6004a5c7b75119fd254c56f60d0d33928693a8ed8103fc92e5a
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -127.27854279879867, "std_reward": 70.85691124535785, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-28T10:16:39.869504"}
+{"env_id": "LunarLander-v2", "mean_reward": -113.79116115661228, "std_reward": 36.264599122125155, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-28T10:28:29.044135"}