地平線イマジネーション：拡散ワールドモデルにおける効率的なオンポリシーロールアウト
Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
拡散ベースのワールドモデルで、複数の将来観測を並列にノイズ除去するオンポリシー・イマジネーション手法を提案し、計算コストを抑えつつ制御性能を維持できることを示した。
著者: Lior Cohen, Ofir Nabati, Kaixin Wang, Navdeep Kumar, Shie Mannor
分類: cs.LG
原文アブストラクト
We study diffusion-based world models for reinforcement learning, which offer high generative fidelity but face critical efficiency challenges in control. Current methods either require heavyweight models at inference or rely on highly sequential imagination, both of which impose prohibitive computational costs. We propose Horizon Imagination (HI), an on-policy imagination process for discrete stochastic policies that denoises multiple future observations in parallel. HI incorporates a stabilization mechanism and a novel sampling schedule that decouples the denoising budget from the effective horizon over which denoising is applied while also supporting sub-frame budgets. Experiments on Atari 100K and Craftium show that our approach maintains control performance with a sub-frame budget of half the denoising steps and achieves superior generation quality under varied schedules. Code is available at https://github.com/leor-c/horizon-imagination.