Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -146.20 +/- 83.69
+      value: -83.87 +/- 44.20
       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': 1500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1707488270.1911b2b6a1f0.3472.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc586685db820e2ce1b68660b840da1b89c6ce5eaadb9427a6991a7f5647c8b3
+size 1988938

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:f405cf84bef10fcdfb94f125f3cb185985a9378a39ffd0461089399000ae1925
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -146.1995114902098, "std_reward": 83.69422766218412, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T12:37:18.680919"}
+{"env_id": "LunarLander-v2", "mean_reward": -83.87054965012346, "std_reward": 44.19668552410001, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T14:54:22.197453"}