Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -168.50 +/- 111.88
+      value: -161.68 +/- 83.93
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1705703494.55e367ee5194.4679.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568da2c7fa64bf33b737ac75628743a1d3ac9b33946d2cc4c7cd3d9f879daa54
+size 110096

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac1132b34cd37aa87733061e6a98553092d12cd0f7def24c3ac087df8388a48
+oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -168.50254454106252, "std_reward": 111.88310490936777, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-19T22:30:54.354335"}
+{"env_id": "LunarLander-v2", "mean_reward": -161.67979999917628, "std_reward": 83.92530409670987, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-19T22:32:17.259516"}