Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -106.83 +/- 87.57
+      value: -140.20 +/- 62.56
       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': 0.0001
+'learning_rate': 0.00016
 'num_envs': 4
 'num_steps': 192
 'anneal_lr': True

logs/events.out.tfevents.1691894859.4c5d58e91a6c.225.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b6b47893d1ae15e6a649bb8a248824ec9f82860f65d65b245845aef630463e
+size 187277

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9350b1b7c6d4e43f5d5202fc8456eb98d4577f04aa0e9a839e1e704aa7175bbf
+oid sha256:cdfa2029b0aefea0215b61fe163f1e53ff36690e3b2ce4534e8cdd6093c16207
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -106.8300660569799, "std_reward": 87.57369656844713, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:47:14.949731"}
+{"env_id": "LunarLander-v2", "mean_reward": -140.20012366988448, "std_reward": 62.55615038566897, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:49:07.357596"}