Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -139.29 +/- 48.76
+      value: -49.77 +/- 19.51
       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': 16
 'num_steps': 128

logs/events.out.tfevents.1692529784.3a0c42a9f836.15451.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6df5afcb3d3e329ba9134cbfb0e5864e599281434a4375e4819f54409efd25
+size 527609

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b322f1744bc2e755e206e961b44e3528aae3b49252895b8a8594e63a25676e
+oid sha256:d9b14eb65015a3d58c6311accf63829a2516ef8b480f8ca9d4582bf8e18d80b9
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -139.2897927394428, "std_reward": 48.76418654432068, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-20T11:08:12.479500"}
+{"env_id": "LunarLander-v2", "mean_reward": -49.76632175469464, "std_reward": 19.514991340927573, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-20T11:31:42.246031"}