Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 132.06 +/- 46.81
+      value: -28.34 +/- 14.96
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 2000000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 128
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.99999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'hui168/ppo-LunarLander-v2-from-scratch'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1712872622.e9e41f7c5b7d.27071.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2e9453c6725d86975da893623299e4b92946ec50b96e46d30036e8aa9d5143
+size 805481

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7724abd1480732d3ec310d78c76da7eca3f13e01f7fc619206d5b5910bef2376
+oid sha256:1ba0033f941b7d0f2b3dbc70518866e65bda85bda2c35db68f57e30563664dc8
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 132.06084617443258, "std_reward": 46.80571882245905, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-11T21:19:57.836045"}
+{"env_id": "LunarLander-v2", "mean_reward": -28.338419955831064, "std_reward": 14.964513522606394, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-11T23:01:44.070491"}