Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -148.82 +/- 78.38
+      value: -139.29 +/- 48.76
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 4
+'num_envs': 16
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'Ding-Qiang/ppo-LunarLander-v2-from-scratch'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1692529670.3a0c42a9f836.14928.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb853ae561d4b428d5d895708843fde33e80cee2dcf5823d1e9fb30f13ebef9e
+size 69655

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba9eba95178b8c1eeff91f1866f65cb2c8b1c65ceedc704e4da139555fb0614
+oid sha256:92b322f1744bc2e755e206e961b44e3528aae3b49252895b8a8594e63a25676e
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -148.81955400589231, "std_reward": 78.37687805498184, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-20T11:04:17.002771"}
+{"env_id": "LunarLander-v2", "mean_reward": -139.2897927394428, "std_reward": 48.76418654432068, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-20T11:08:12.479500"}