Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -147.57 +/- 86.64
+      value: -98.73 +/- 60.63
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 25000
+'total_timesteps': 100000
 'torch_deterministic': True
 'cuda': True
 'track': False

logs/events.out.tfevents.1697204504.4c732871a5f0.209.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca3d5b890b9decad3d411bc460b1be120da7767c35f1cd75fd1b9ae8fadfe91
+size 221333

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58442693c6d40c6c6e1a891d98b580d8980a65d0809aa8cf5d1d20c31a017318
+oid sha256:8802a401f9eedb07ef810eb6d49c91ffd77d753bd96675776004777157abd97e
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -147.56791876346006, "std_reward": 86.63615973606748, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-13T13:37:15.092401"}
+{"env_id": "LunarLander-v2", "mean_reward": -98.72626699500645, "std_reward": 60.628357927535255, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-13T13:43:07.495012"}