Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -226.13 +/- 120.49
+      value: -154.08 +/- 64.46
       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.1740322782.a47af9a784dd.12935.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e90edbf866fe92c7430b0531c61bc1b3aed962d53f91880dfef5b80da7dd05
+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": -226.1264465298948, "std_reward": 120.49444107875668, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-23T14:58:56.978398"}
+{"env_id": "LunarLander-v2", "mean_reward": -154.08045260545376, "std_reward": 64.46189669950436, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-23T15:00:24.170844"}