Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 150.87 +/- 123.22
+      value: 64.69 +/- 15.69
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 1000000
 'learning_rate': 0.001
 'num_envs': 4
-'num_steps': 128
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'crossroderick/ppo-unit8-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1710256991.28d9d214646f.31308.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8aaccfc5cec9dec7fa90b81f9e8516eb355ef095eeda3f6530a40c9243ed817
+size 316886

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3de01bf119eba146ac24541cba34cb0131b1b8bf34d28122ae0b978abbe96bd0
+oid sha256:1275e8c779e237efeb16d984a3b4b26f5ca70c3673afbfae0d96181f636a99f9
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 150.87450746432933, "std_reward": 123.22120469166885, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-12T15:20:04.623096"}
+{"env_id": "LunarLander-v2", "mean_reward": 64.69184515009965, "std_reward": 15.691810262154094, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-12T15:51:20.436292"}