Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -111.51 +/- 61.92
+      value: -55.01 +/- 35.26
       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': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1725012893.d0e75d0d91c9.4124.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac22a8173f19f4326ca21d0e50707d91b7f6019c2f6a4d05ec1a35fe20874b47
+size 673755

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:f77ef9c75a6010d53b638b2fbf6a0a2a078997ab1d6d29a1b7ff740ac1d0c4bf
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -111.5093388201658, "std_reward": 61.92350493330615, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-30T10:13:44.411576"}
+{"env_id": "LunarLander-v2", "mean_reward": -55.011501433750084, "std_reward": 35.26371539086687, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-30T10:29:07.458152"}