paper-with-me

Papers

The Statistical Complexity of Interactive Decision Making

2021-12-27 · Dylan J. Foster, Sham M. Kakade, Jian Qian, Alexander Rakhlin

A fundamental challenge in interactive learning and decision making, ranging from bandit problems to reinforcement learning, is to provide sample-efficient, adaptive learning algorithms that achieve near-optimal regret. This question is analogous to the classical problem of optimal (supervised) statistical learning, where there are well-known complexity measures (e.g., VC dimension and Rademacher complexity) that govern the statistical complexity of learning. However, characterizing the statistical complexity of interactive learning is substantially more challenging due to the adaptive nature of the problem. The main result of this work provides a complexity measure, the Decision-Estimation Coefficient, that is proven to be both necessary and sufficient for sample-efficient interactive learning. In particular, we provide: 1. a lower bound on the optimal regret for any interactive decision making problem, establishing the Decision-Estimation Coefficient as a fundamental limit. 2. a unified algorithm design principle, Estimation-to-Decisions (E2D), which transforms any algorithm for supervised estimation into an online algorithm for decision making. E2D attains a regret bound that matches our lower bound up to dependence on a notion of estimation performance, thereby achieving optimal sample-efficient learning as characterized by the Decision-Estimation Coefficient. Taken together, these results constitute a theory of learnability for interactive decision making. When applied to reinforcement learning settings, the Decision-Estimation Coefficient recovers essentially all existing hardness results and lower bounds. More broadly, the approach can be viewed as a decision-theoretic analogue of the classical Le Cam theory of statistical estimation; it also unifies a number of existing approaches -- both Bayesian and frequentist.

📄 PDF Abstract BibTeX arXiv:2112.13487

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Makingreinforcement-learningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

CAM Class activation maps could be used to interpret the prediction decision made by the convolutional neural network (CNN). Image source: [Learning Deep Features for…

Similar Papers 제목 키워드 기반

Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability

2024-10-07 · Fan Chen, Dylan J. Foster, Yanjun Han, Jian Qian 외

We develop a unifying framework for information-theoretic lower bound in statistical estimation and interactive decision making. Classical lower bound techniques -- such as Fano's method, Le Cam's method, and Assouad's l…

Decision MakingLEMMA

On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring

2023-05-01 · Dylan J. Foster, Dean P. Foster, Noah Golowich, Alexander Rakhlin

A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees, and how these consideratio…

Decision MakingMulti-agent Reinforcement Learning

Model-Free Reinforcement Learning with the Decision-Estimation Coefficient

2022-11-25 · NeurIPS 2023 11

We consider the problem of interactive decision making, encompassing structured bandits and reinforcement learning with general function approximation. Recently, Foster et al. (2021) introduced the Decision-Estimation Co…

Decision Makingreinforcement-learningReinforcement Learning

Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient

2023-01-19 · Dylan J. Foster, Noah Golowich, Yanjun Han

A foundational problem in reinforcement learning and interactive decision making is to understand what modeling assumptions lead to sample-efficient learning guarantees, and what algorithm design principles achieve optim…

Decision Makingreinforcement-learningReinforcement Learning (RL)

Online Estimation via Offline Estimation: An Information-Theoretic Framework

2024-04-15 · Dylan J. Foster, Yanjun Han, Jian Qian, Alexander Rakhlin

$ $The classical theory of statistical estimation aims to estimate a parameter of interest under data generated from a fixed design ("offline estimation"), while the contemporary theory of online learning provides algori…

Decision MakingDensity Estimation