Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -102.67 +/- 94.53
+      value: -0.07 +/- 107.09
       name: mean_reward
       verified: false
 ---
@@ -39,8 +39,8 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
 'learning_rate': 0.00025
-'num_envs': 16
-'num_steps': 1024
+'num_envs': 4
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'jth5220/ppo-LunarLander-v2'
-'batch_size': 16384
-'minibatch_size': 4096}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1738747384.bb67e88a0492.12981.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712b4043f1ed32f4f53f31b09821f28e1a63be7ae8204ca4e938f53cd1f53ce0
+size 1255268

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f06f86b0f26ceed1c1ab3121505d98c920afd020e5ed4fa72b8e9f6fa3524e3
+oid sha256:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -102.67485093110584, "std_reward": 94.5260022611971, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-05T09:11:30.256509"}
+{"env_id": "LunarLander-v2", "mean_reward": -0.0665043279116361, "std_reward": 107.09108579646897, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-05T09:50:41.244238"}