Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -119.69 +/- 40.93
+      value: -65.89 +/- 48.70
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'f': '/root/.local/share/jupyter/runtime/kernel-13ae2347-2156-49eb-80c5-a8b483ae1b52.json'
 'env_id': 'LunarLander-v2'
-'total_timesteps': 250000
+'total_timesteps': 5000000
 'learning_rate': 0.00022
 'num_envs': 16
 'num_steps': 256

logs/events.out.tfevents.1691881829.f7c6ccb2950d.678.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f18fce460d246f85fb79671944edf14759d36eb7a2aae76e8afedca8aac834e8
+size 1589776

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:499a30ac8ed4e62158bcc9bfb08527fc70c2a83a2fcb112252276447e25567ae
+oid sha256:15cb7f56f995a36665aa0d7fe1829234173cb37faa85c82c17de17df4a2b70ac
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -119.68585316751664, "std_reward": 40.93082158469233, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-12T23:09:22.933489"}
+{"env_id": "LunarLander-v2", "mean_reward": -65.88774618288689, "std_reward": 48.70327928360739, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T01:12:02.509462"}