Deciding What to Learn: A Rate-Distortion Approach

v1v2v3 (latest)

Deciding What to Learn: A Rate-Distortion Approach

15 January 2021

Benjamin Van Roy

ArXiv (abs)PDF HTML

Papers citing "Deciding What to Learn: A Rate-Distortion Approach"

18 / 18 papers shown

Title
Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images Tian Qiu Arjun Nichani Rasta Tadayontahmasebi Haewon Jeong 66 0 0 05 May 2025
Satisficing Exploration for Deep Reinforcement Learning Dilip Arumugam Saurabh Kumar Ramki Gummadi Benjamin Van Roy 67 1 0 16 Jul 2024
Exploration Unbound Dilip Arumugam Wanqiao Xu Benjamin Van Roy 75 0 0 16 Jul 2024
Learning telic-controllable state representations Nadav Amir Stas Tiomkin Angela Langdon 92 0 0 20 Jun 2024
On Bits and Bandits: Quantifying the Regret-Information Trade-off Itai Shufaro Nadav Merlis Nir Weinberger Shie Mannor 199 0 0 26 May 2024
Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning Qiaosheng Zhang Chenjia Bai Shuyue Hu Zhen Wang Xuelong Li 113 1 0 30 Apr 2024
Information Capacity Regret Bounds for Bandits with Mediator Feedback Khaled Eldowa Nicolò Cesa-Bianchi Alberto Maria Metelli Marcello Restelli 49 2 0 15 Feb 2024
Efficient Exploration for LLMs Vikranth Dwaracherla S. Asghari Botao Hao Benjamin Van Roy LLMAG 95 22 0 01 Feb 2024
Domain Generalization without Excess Empirical Risk Ozan Sener V. Koltun 74 9 0 30 Aug 2023
Bayesian Reinforcement Learning with Limited Cognitive Load Dilip Arumugam Mark K. Ho Noah D. Goodman Benjamin Van Roy OffRL 86 8 0 05 May 2023
Online Learning-based Waveform Selection for Improved Vehicle Recognition in Automotive Radar C. Thornton William W. Howard R. M. Buehrer 50 2 0 01 Dec 2022
On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning Dilip Arumugam Mark K. Ho Noah D. Goodman Benjamin Van Roy 91 4 0 30 Oct 2022
Linear Jamming Bandits: Sample-Efficient Learning for Non-Coherent Digital Jamming C. Thornton R. M. Buehrer 21 4 0 05 Jul 2022
Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning Dilip Arumugam Benjamin Van Roy OffRL 80 15 0 04 Jun 2022
Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning Dilip Arumugam Benjamin Van Roy OffRL 70 1 0 04 Jun 2022
Non-Stationary Bandit Learning via Predictive Sampling Yueyang Liu Kuang Xu Benjamin Van Roy 124 18 0 04 May 2022
The Value of Information When Deciding What to Learn Dilip Arumugam Benjamin Van Roy 75 12 0 26 Oct 2021
Reinforcement Learning, Bit by Bit Xiuyuan Lu Benjamin Van Roy Vikranth Dwaracherla M. Ibrahimi Ian Osband Zheng Wen 126 70 0 06 Mar 2021