Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 148.25 +/- 119.88
+      value: 106.07 +/- 53.15
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 128
+'num_steps': 512
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'gstaff/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1677458400.25f188cb86e1.50972.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8051ff833e771edb47c721b349d52bfb9949cb820771d2301623ff86041b700
+size 722326

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb0737f6845ed8170f6c0991ec58092649513a8e3acc13f79799492780d82fc
+oid sha256:ae0d6aa21e271da69955977a6403945a3d8a221472f1f4163801d505f7fb9ccf
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 148.24975951966937, "std_reward": 119.87536434353854, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T00:33:05.159835"}
+{"env_id": "LunarLander-v2", "mean_reward": 106.0703485949823, "std_reward": 53.145236412589945, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T00:59:49.106318"}