5 papers
Best Agent Identification for General Game Playing
Matthew Stephenson, Alex Newcombe, Eric Piette +1
We present an efficient and generalised procedure to accurately identify the best (or near best) performing algorithm for each sub-task in a multi-problem domain. Our approach trea…
An Ambiguous State Machine
Matt Stephenson
We show that a replicated state machine (such as a blockchain protocol) can retain liveness in a strategic setting even while facing substantial ambiguity over certain events. This…
NDAI Agreements
Matthew Stephenson, Andrew Miller, Xyn Sun +2
We study a fundamental challenge in the economics of innovation: an inventor must reveal details of a new idea to secure compensation or funding, yet such disclosure risks expropri…
Towards Bio-inspired Heuristically Accelerated Reinforcement Learning for Adaptive Underwater Multi-Agents Behaviour
Antoine Vivien, Thomas Chaffre, Matthew Stephenson +4
This paper describes the problem of coordination of an autonomous Multi-Agent System which aims to solve the coverage planning problem in a complex environment. The considered appl…
GAVEL: Generating Games Via Evolution and Language Models
Graham Todd, Alexander Padula, Matthew Stephenson +3
Automatically generating novel and interesting games is a complex task. Challenges include representing game rules in a computationally workable form, searching through the large s…