Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -106.39 +/- 66.90
+      value: -50.24 +/- 51.91
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'f': '/root/.local/share/jupyter/runtime/kernel-034b7df4-145b-4db4-9d09-b6d875ced33d.json'
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.0005
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1691893782.4c5d58e91a6c.225.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37551c019e480c8010607f95ba0390a1e7a80a1dae4cdca7219260294292c21c
+size 178900

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8eababea371232ac3230ce4bad19a8bc6793ef2a76e418478be41c0668c4852
+oid sha256:88eba4cfd6068b53d2e0f7811632e663f21280b1aa6efad4dbb135dcd2e96030
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -106.39441727212122, "std_reward": 66.9044527194171, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:29:19.834559"}
+{"env_id": "LunarLander-v2", "mean_reward": -50.23883619861744, "std_reward": 51.90562707277743, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:31:32.703903"}