Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -5.45 +/- 79.09
+      value: 221.50 +/- 80.82
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 1000000
 'learning_rate': 0.005
 'num_envs': 4
 'num_steps': 1024

logs/events.out.tfevents.1691965616.315c1a329dea.1523.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d712232dc42cc1b23b5769fe11985494c397c23506a045e0f2be855cede8c8
+size 413312

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7582ef64c8b34ee5c269f46476f468eb298019685016c7c0bc994186f0e28f02
+oid sha256:b0f968bda0fa94dbd9f34b17c1a4e07ca234458d53afdb20a7b01d1a1903eb08
 size 8452763

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -5.451203603990123, "std_reward": 79.0900509828269, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T21:59:58.525257"}
+{"env_id": "LunarLander-v2", "mean_reward": 221.50016292291608, "std_reward": 80.81726391947741, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T22:51:43.139828"}