Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -189.58 +/- 78.12
+      value: -10.35 +/- 65.13
       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': 250000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1680971519.7c1450dee134.5276.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a47d7810ceea9124b52a21954f56e2f4474c9bd5aaeac39b18fc55f81aabc8
+size 392309

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a363dfe098933c96feb65ea5062a91e8aacf7448c05ac211c1404fb4e0f78d9
+oid sha256:1a5bdeb16cb68de637c50dea5cf7cf3ce3f0c05e4ee975aa094249d447152579
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -189.58418679268732, "std_reward": 78.12199572605537, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-08T16:28:05.962478"}
+{"env_id": "LunarLander-v2", "mean_reward": -10.349440898346652, "std_reward": 65.1313220503084, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-08T16:37:30.392768"}