paper-with-me

Papers

Symmetry-Breaking Augmentations for Ad Hoc Teamwork

2024-02-15 · Ravi Hammond, Dustin Craggs, Mingyu Guo, Jakob Foerster, Ian Reid

In many collaborative settings, artificial intelligence (AI) agents must be able to adapt to new teammates that use unknown or previously unobserved strategies. While often simple for humans, this can be challenging for AI agents. For example, if an AI agent learns to drive alongside others (a training set) that only drive on one side of the road, it may struggle to adapt this experience to coordinate with drivers on the opposite side, even if their behaviours are simply flipped along the left-right symmetry. To address this we introduce symmetry-breaking augmentations (SBA), which increases diversity in the behaviour of training teammates by applying a symmetry-flipping operation. By learning a best-response to the augmented set of teammates, our agent is exposed to a wider range of behavioural conventions, improving performance when deployed with novel teammates. We demonstrate this experimentally in two settings, and show that our approach improves upon previous ad hoc teamwork results in the challenging card game Hanabi. We also propose a general metric for estimating symmetry-dependency amongst a given set of policies.

📄 PDF Abstract BibTeX arXiv:2402.09984

Code (0)

등록된 구현이 없습니다.

Tasks

AI AgentDiversity

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
HOC 설명 없음

Similar Papers 제목 키워드 기반

Equivariant Symmetry Breaking Sets

2024-02-05 · Yuqing Xie, Tess Smidt

Equivariant neural networks (ENNs) have been shown to be extremely effective in applications involving underlying symmetries. By construction ENNs cannot produce lower symmetry outputs given a higher symmetry input. Howe…

Symmetry Breaking in Neural Network Optimization: Insights from Input Dimension Expansion

2024-09-10 · Jun-Jie Zhang, Nan Cheng, Fu-Peng Li, Xiu-Cheng Wang 외

Understanding the mechanisms behind neural network optimization is crucial for improving network design and performance. While various optimization techniques have been developed, a comprehensive understanding of the und…

On the Complexity of Breaking Symmetry

2020-05-16 · Toby Walsh

We can break symmetry by eliminating solutions within a symmetry class that are not least in the lexicographical ordering. This is often referred to as the lex-leader method. Unfortunately, as symmetry groups can be larg…

Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution

2023-10-03 · Rui Wang, Elyssa Hofgard, Han Gao, Robin Walters 외

Modeling symmetry breaking is essential for understanding the fundamental changes in the behaviors and properties of physical systems, from microscopic particle interactions to macroscopic phenomena like fluid dynamics a…

Super-Resolution

Analyzing symmetry and symmetry breaking by computational aesthetic measures

2019-10-15 · Hendrik Richter

We study creating and analyzing symmetry and broken symmetry in digital art. Our focus is not so much on computer-generating artistic images, but rather on analyzing concepts and templates for incorporating symmetry and …

Sand