Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -74.00 +/- 43.75
+      value: -129.85 +/- 108.24
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 128
+'num_steps': 2048
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'jarski/myppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 8192
+'minibatch_size': 2048}
   ```
   

logs/events.out.tfevents.1725020036.bd5e60046b14.13494.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce3308e893aa0261105ec27f06e6e5374c49c70df44f3be457ca187abbc1385
+size 134276

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bab62617dee61f1306b075d08c5031f47552a39ea30c380840904fab1b528b7
+oid sha256:d20057b4ac95b70918430eaeb734caf8ed27b8a45cbd98715a65469438dc4ad2
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -73.99645913190177, "std_reward": 43.74678801966028, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-30T12:07:18.868967"}
+{"env_id": "LunarLander-v2", "mean_reward": -129.8529374063792, "std_reward": 108.24423083037863, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-30T12:15:04.196146"}