Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -209.71 +/- 141.44
+      value: -129.83 +/- 94.89
       name: mean_reward
       verified: false
 ---
@@ -32,12 +32,12 @@ model-index:
 'seed': 1
 'torch_deterministic': True
 'cuda': True
-'track': False
+'track': True
 'wandb_project_name': 'ppo-implementation'
-'wandb_entity': None
+'wandb_entity': 'arina-iusupova-ai-university-of-klagenfurt'
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1740321573.a47af9a784dd.7837.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd3f1fef822058c1eb6ef7e3097546fe53e2d7616109b55bbcd6f43d5f467c8
+size 110137

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303b13a66abf6da109190061aa9f1d1a675dde181867f69be252aaaa922d99f4
+oid sha256:339f09e8b06f686b9c10d26099e14e7a7303e9b6ecce9f9f6a67b3d5b02b6551
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -209.70861377327282, "std_reward": 141.43696826529037, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-23T14:38:33.986501"}
+{"env_id": "LunarLander-v2", "mean_reward": -129.8258789607068, "std_reward": 94.89435187134733, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-23T14:40:15.803561"}