Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -176.62 +/- 95.81
+      value: -128.94 +/- 87.14
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 1024
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.9
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'jfelgate/ppo-LunarLander-v2'
-'batch_size': 4096
-'minibatch_size': 1024}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1698072626.527fe3665085.25230.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:162f37fec7429b6672114a7f0edee04e50615bcff19eed6006c79f7fb1a6950a
+size 85465

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e877e327c37e38355e589831a8bf9a9137c34b031f902e346ce8080cf2c11701
+oid sha256:8fa2f6fac6eb7b6411a0149a887c9f7ab56ee6f49340bc59ff494f622b2003c1
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -176.61866016938296, "std_reward": 95.81393100407745, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:47:51.086564"}
+{"env_id": "LunarLander-v2", "mean_reward": -128.9358893690048, "std_reward": 87.13581962908091, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:51:32.531005"}