SOURCE-LINKED INTELLIGENCE

Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

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 discount factors arbitrarily close to one. It was therefore unknown whether the problem remains hard for any discount factor, and whether near-optimal planning can nevertheless be performed efficiently

Read original source ↗ Open in workspace

recordType

paper

region

Global