Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -41.43 +/- 82.99
+      value: -17.70 +/- 64.82
       name: mean_reward
       verified: false
 ---
@@ -52,7 +52,7 @@ model-index:
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
-'max_grad_norm': 0.1
+'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'DavidCollier/ppo-LunarLander-v2-unit8'
 'batch_size': 512

logs/events.out.tfevents.1704519488.cef9efba8278.7167.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4190f7ad600da7a90c04a89e58f101fac90b3d03d9844e92bcc3dc18544acc95
+size 74958

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa5d3a60127dd4acfcf2b3409fdfa3b0e1badffd4f47e6f9ecb6f68272887793
+oid sha256:03fea06edadcd8762cd908556a6a88cdfc153d80f30c925edcdb4ccb76de9e74
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -41.43157712959779, "std_reward": 82.9885349684779, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-06T05:37:07.124234"}
+{"env_id": "LunarLander-v2", "mean_reward": -17.69836714356797, "std_reward": 64.82119091148782, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-06T05:39:26.631672"}