paper-with-me

Papers

Discovery of Useful Questions as Auxiliary Tasks

2019-09-10 · NeurIPS 2019 12 · Vivek Veeriah, Matteo Hessel, Zhongwen Xu, Richard Lewis, Janarthanan Rajendran, Junhyuk Oh, Hado van Hasselt, David Silver, Satinder Singh

Arguably, intelligent agents ought to be able to discover their own questions so that in learning answers for them they learn unanticipated useful knowledge and skills; this departs from the focus in much of machine learning on agents learning answers to externally defined questions. We present a novel method for a reinforcement learning (RL) agent to discover questions formulated as general value functions or GVFs, a fairly rich form of knowledge representation. Specifically, our method uses non-myopic meta-gradients to learn GVF-questions such that learning answers to them, as an auxiliary task, induces useful representations for the main task faced by the RL agent. We demonstrate that auxiliary tasks based on the discovered GVFs are sufficient, on their own, to build representations that support main task learning, and that they do so better than popular hand-designed auxiliary tasks from the literature. Furthermore, we show, in the context of Atari 2600 videogames, how such auxiliary tasks, meta-learned alongside the main task, can improve the data efficiency of an actor-critic agent.

📄 PDF Abstract BibTeX arXiv:1909.04607

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Auxiliary task discovery through generate-and-test

2022-10-25 · Banafsheh Rafiee, Sina Ghiassian, Jun Jin, Richard Sutton 외

In this paper, we explore an approach to auxiliary task discovery in reinforcement learning based on ideas from representation learning. Auxiliary tasks tend to improve data efficiency by forcing the agent to learn auxil…

Meta-LearningRepresentation Learning

What makes useful auxiliary tasks in reinforcement learning: investigating the effect of the target policy

2022-04-01 · Banafsheh Rafiee, Jun Jin, Jun Luo, Adam White

Auxiliary tasks have been argued to be useful for representation learning in reinforcement learning. Although many auxiliary tasks have been empirically shown to be effective for accelerating learning on the main task, i…

Representation Learning

Auxiliary Learning by Implicit Differentiation

2020-06-22 · ICLR 2021 1 · Aviv Navon, Idan Achituve, Haggai Maron, Gal Chechik 외

Training neural networks with auxiliary tasks is a common practice for improving the performance on a main task of interest. Two main challenges arise in this multi-task learning setting: (i) designing useful auxiliary t…

Auxiliary LearningImage ClassificationImage SegmentationMulti-Task Learning+2

Few-Shot Design Optimization by Exploiting Auxiliary Information

2026-02-12 · Arjun Mani, Carl Vondrick, Richard Zemel arxiv

Many real-world design problems involve optimizing an expensive black-box function $f(x)$, such as hardware design or drug discovery. Bayesian Optimization has emerged as a sample-efficient framework for this problem. Ho…

Drug Discovery

MultiOpEd: A Corpus of Multi-Perspective News Editorials

2021-06-04 · NAACL 2021 4 · Siyi Liu, Sihao Chen, Xander Uyttendaele, Dan Roth

We propose MultiOpEd, an open-domain news editorial corpus that supports various tasks pertaining to the argumentation structure in news editorials, focusing on automatic perspective discovery. News editorial is a genre …

Multi-Task LearningSentence