Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -128.18 +/- 73.27
+      value: -40.80 +/- 79.36
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 150000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1676547072.39fde2301556.4270.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b280bc43ca8297c759a0c4532762e6221656b4fab920a100b8d29b44b9ee227
+size 269237

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:86b8edb8296972098e59c6fd3d401bc5edf2268d803e7e1d9d78c1ed9e8321d7
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -128.18128698789883, "std_reward": 73.26721133237012, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T11:30:25.926461"}
+{"env_id": "LunarLander-v2", "mean_reward": -40.803086852895056, "std_reward": 79.35870833383824, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T11:34:08.990966"}