Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -74.84 +/- 33.01
+      value: -106.39 +/- 66.90
       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': 0.00024
+'learning_rate': 0.0005
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1691893676.4c5d58e91a6c.225.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb9ff7715830d19d398568be0b9202c27f6e2be99af37daf0b56deed5378145
+size 221907

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe4bad068f1aeeb787f57574e8a9a71540801921c50451557fa92b9e5101caf4
+oid sha256:b8eababea371232ac3230ce4bad19a8bc6793ef2a76e418478be41c0668c4852
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -74.8416016528234, "std_reward": 33.00754289204665, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:26:33.269902"}
+{"env_id": "LunarLander-v2", "mean_reward": -106.39441727212122, "std_reward": 66.9044527194171, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:29:19.834559"}