paper-with-me

홈 › Papers

Coarse-Grained Smoothness for RL in Metric Spaces

2021-10-23 · Omer Gottesman, Kavosh Asadi, Cameron Allen, Sam Lobel, George Konidaris, Michael Littman

Principled decision-making in continuous state--action spaces is impossible without some assumptions. A common approach is to assume Lipschitz continuity of the Q-function. We show that, unfortunately, this property fails to hold in many typical domains. We propose a new coarse-grained smoothness definition that generalizes the notion of Lipschitz continuity, is more widely applicable, and allows us to compute significantly tighter bounds on Q-functions, leading to improved learning. We provide a theoretical analysis of our new smoothness definition, and discuss its implications and impact on control and exploration in continuous domains.

📄 PDF Abstract BibTeX arXiv:2110.12276

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

CoFi-UCGen: Coarse-to-Fine Unsupervised Conditional Generation without Label Priors

2026-06-04 · Shengxi Li, Zhaokun Hu, Ce Zheng, Mai Xu 외 arxiv

Unsupervised conditional image generation (UCGen) aims to control generation without relying on manually annotated labels, yet remains challenging due to unstructured semantic representations across granularities. To add…

Conditional Image Generation

Optimal Learning with Anisotropic Gaussian SVMs

2018-10-04 · Hanyuan Hang, Ingo Steinwart

This paper investigates the nonparametric regression problem using SVMs with anisotropic Gaussian RBF kernels. Under the assumption that the target functions are resided in certain anisotropic Besov spaces, we establish …

regression

The Latent Road to Atoms: Backmapping Coarse-grained Protein Structures with Latent Diffusion

2024-10-17 · Xu Han, Yuancheng Sun, Kai Chen, Kang Liu 외

Coarse-grained(CG) molecular dynamics simulations offer computational efficiency for exploring protein conformational ensembles and thermodynamic properties. Though coarse representations enable large-scale simulations a…

Computational EfficiencyDenoising

Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We study the problem of coarse-grained response selection in retrieval-based dialogue systems. The problem is equally important with fine-grained response selection, but is less explored in existing literature. In this p…

Retrieval

Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations

2021-09-24 · ACL 2022 5 · Wei Chen, Yeyun Gong, Can Xu, Huang Hu 외

We study the problem of coarse-grained response selection in retrieval-based dialogue systems. The problem is equally important with fine-grained response selection, but is less explored in existing literature. In this p…

Retrieval