Paper recorded by Signals 4 on 2026-09-10 in cs.LG. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-10 on arXiv · recorded by Signals 4 on 2026-09-11
Category: cs.LG · 机器学习 · first seen 2026-09-11
We study reinforcement learning (RL) with transition look-ahead, where the agent may observe which states would be visited upon playing any sequence of $\ell$ actions before deciding its course of action. Although look-ahead can substantially improve achievable performance, it is known that optimal planning with multi-step transition look-ahead is NP-hard, but this hardness was established using d