Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -63.54 +/- 150.03
+      value: -79.35 +/- 79.28
       name: mean_reward
       verified: false
 ---
@@ -31,9 +31,9 @@ model-index:
   {'exp_name': 'ppo'
 'repo_id': 'PhysHunter/ippo-LunarLander-v2'
 'env_id': 'LunarLander-v2'
-'learning_rate': 0.01
+'learning_rate': 0.001
 'seed': 1
-'total_timesteps': 50000
+'total_timesteps': 100000
 'torch_deterministic': True
 'cuda': True
 'record_video': None

logs/events.out.tfevents.1686529301.4c7cbfaa41ac.54429.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0e21f0dff2227b74b81ba311c06fdb258ffefa7bd2107a112d123629de5e6aa
+size 166402

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a91b75e276b0894ebbb67d851e352a8430c6e93f624fd47ba9b64e7f015dc92
+oid sha256:8585db8a3c8c74c7d64b1a8aa9401541049aa634a14861faa094f5df6dd4ffb8
 size 6949

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -63.53524299484243, "std_reward": 150.0316075335214, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T00:20:18.330236"}
+{"env_id": "LunarLander-v2", "mean_reward": -79.35319189485695, "std_reward": 79.27976617596882, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T00:23:51.165076"}