Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -144.28 +/- 106.51
+      value: -117.96 +/- 96.83
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 500000
 'learning_rate': 2e-05
 'num_envs': 4
-'num_steps': 128
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'FBM/LunarLander-Manual'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 1024
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1678359959.de9c9160a6a5.39792.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab78663705c96edbbedb466bb70f871163f7961a8fa34bbdb16df0653a2ee1a5
+size 872632

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eacb7a0179cec67a2b77f51069c0f94b44b4b94df1594d50b8ba25a031f0f821
+oid sha256:32fafed7c99cfae4cb09c6dfb7f799de17a117108938fca897216cd11dbfab4f
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -144.27636793567547, "std_reward": 106.50855328603998, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-09T11:04:03.659960"}
+{"env_id": "LunarLander-v2", "mean_reward": -117.95584882194075, "std_reward": 96.8333968536081, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-09T11:13:15.113139"}