Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -168.92 +/- 122.32
+      value: 193.23 +/- 73.78
       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': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1682613953.1cc71a86c156.12781.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9c0b63343dd4a259122825d66d9de83f5f78dc200ef47caeb6071c2d88fc63
+size 1342443

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c9b4d16b6ed7cfbc262be34c3c53bdcd2df87c2abe0a3318b12d0ad8723331
+oid sha256:713491676944f6d281167b5e72f31b8a365ff072a5699500e80a1551aaaa379e
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -168.9248586460796, "std_reward": 122.31541747592047, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-27T16:42:03.462314"}
+{"env_id": "LunarLander-v2", "mean_reward": 193.22675721060727, "std_reward": 73.77594181690823, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-27T17:10:20.113340"}