Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -156.24 +/- 87.61
+      value: -42.61 +/- 61.76
       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': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1706778472.9faf87810308.7448.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c484c1aff8c674334e3872d4ef0ed9efcfba18ab6043bcc3b197943ba940507
+size 1235299

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:4bab62617dee61f1306b075d08c5031f47552a39ea30c380840904fab1b528b7
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -156.24214766765812, "std_reward": 87.60728927873828, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-01T09:04:04.559074"}
+{"env_id": "LunarLander-v2", "mean_reward": -42.61138103414538, "std_reward": 61.76215266345291, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-01T09:36:36.546861"}