Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -135.71 +/- 72.86
+      value: -116.74 +/- 38.53
       name: mean_reward
       verified: false
 ---
@@ -37,9 +37,9 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
-'num_envs': 4
+'num_envs': 8
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'irow/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 1024
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1684422230.irow-pc.63025.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e442544fea5490a48e091e008cf53ad512fb491fe87f8601147533491ea7a19c
+size 168025

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c967ef71a80a7e1b4fd32106591599256d63ca1f8d3e60466f38719a9a5877cb
+oid sha256:ae3a12b982c39cde2729eb9e6d4fe49b9dc5ea651cd83d4285c0bf8269a1a3d0
 size 42817

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -135.70765152619887, "std_reward": 72.86258065489707, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-18T09:01:17.790235"}
+{"env_id": "LunarLander-v2", "mean_reward": -116.74046421620673, "std_reward": 38.53321128828465, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-18T09:04:24.105695"}