Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -168.75 +/- 78.98
+      value: -122.83 +/- 56.60
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 16
 'num_steps': 1024

logs/events.out.tfevents.1699191864.a8bcc0a3658b.7967.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3649b3dccf07ea41545e44784980e9ef165524456f60eb1397a229fc7da20b
+size 1187890

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5702f2b83909dc31a447b9061ed4e18c063d0b6d05ef34ada953045539847f24
+oid sha256:54217be0b876d6c73c9e402d6720eee26b70a83a6fa021edb48d42f7c8e87d45
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -168.7544216734099, "std_reward": 78.97805679161364, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-05T13:43:27.367163"}
+{"env_id": "LunarLander-v2", "mean_reward": -122.83178432650357, "std_reward": 56.59713764776958, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-05T13:49:36.374630"}