Diagnostic-Driven Refinement for Sparse Structured RL
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL
arXiv:2605.28918v1 Announce Type: cross Abstract: For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging than one-shot generation. We study PPO-trained agents using MiniGrid as core evaluation and MuJoCo as boundary stress test. Our audit finds two dominant one-shot failure modes -- reward flooding and semantic/API misunderstanding -- plus a rarer weak-shaping case.