Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -154.08 +/- 64.46
+      value: -121.20 +/- 43.24
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': 'arina-iusupova-ai-university-of-klagenfurt'
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
@@ -53,7 +53,7 @@ model-index:
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
-'target_kl': None
+'target_kl': 0.015
 'repo_id': 'AriYusa/ppo-implementation'
 'batch_size': 512
 'minibatch_size': 128}

logs/events.out.tfevents.1740322971.a47af9a784dd.13807.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca6fa56adbf1e2b449fafb780c63d9189c8e97427f0beb358cc5b926c9563fe
+size 221361

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339f09e8b06f686b9c10d26099e14e7a7303e9b6ecce9f9f6a67b3d5b02b6551
+oid sha256:d044683000e9eb182c8223eb70f158316228f3d297b0325a626f4daf615756b4
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -154.08045260545376, "std_reward": 64.46189669950436, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-23T15:00:24.170844"}
+{"env_id": "LunarLander-v2", "mean_reward": -121.19739618924302, "std_reward": 43.24427141536182, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-23T15:04:07.864397"}