Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -59.21 +/- 64.24
+      value: 35.24 +/- 117.71
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 1000000
 'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1683325792.ef0df3ebac95.14920.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2a73f217e64b023e9d5ec88ce5d4e1f11a0c409e6c54fe6340846df304ebe5
+size 1284288

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ee0f659ecb3e4404cab33908684814d212ecd677a4f843c277d1c42846219fb
+oid sha256:be67ad34969df73a987879f89a9bd76f48d2293059545666fe68889676e65fcb
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -59.21020785878295, "std_reward": 64.23542763948329, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-05T22:25:03.310226"}
+{"env_id": "LunarLander-v2", "mean_reward": 35.23643848761948, "std_reward": 117.71001037893492, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-05T22:58:06.832317"}