Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -166.15 +/- 84.29
+      value: -151.08 +/- 69.28
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 24
+'num_envs': 18
 'num_steps': 1024
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'bee-eater78/ppo-scratch-LunarLander-v1'
-'batch_size': 24576
-'minibatch_size': 6144}
+'batch_size': 18432
+'minibatch_size': 4608}
   ```
   

logs/events.out.tfevents.1720914408.5b2a566f3731.24431.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1d324d15f103d102cd6d69b00a4afc3279f5eed3e452a37208bc3dfb8abc2a
+size 45858

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab1b2eaf5cc06c08b59b2d4eef097c1eb91255cd12dc1fcc1c6f7e09d539fe5
+oid sha256:d07e224d31c02bf069a519e2b9595bf7a5e35d940edd67faa0ba78224abf0685
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -166.14811733134167, "std_reward": 84.28982883988715, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-13T23:45:46.263523"}
+{"env_id": "LunarLander-v2", "mean_reward": -151.0838000444735, "std_reward": 69.27992937665336, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-13T23:47:03.116402"}