Solutions to complex tasks often require the cooperation of multiple robots, however, developing multi-robot policies can present many challenges. In this work, we introduce teach...
We consider the problem of incorporating end-user advice into reinforcement learning (RL). In our setting, the learner alternates between practicing, where learning is based on ac...
Kshitij Judah, Saikat Roy, Alan Fern, Thomas G. Di...
Partially observable Markov decision processes (POMDPs) allow one to model complex dynamic decision or control problems that include both action outcome uncertainty and imperfect ...
Bushfire BLOCKS is a modular, distributed, agent-based simulation for exploring and informing bushfire response strategies. Separate independent modules capture the fire spread, e...
David Scerri, Ferdinand Gouw, Sarah L. Hickmott, I...
: This paper presents a generic agent-based framework for social-mobile applications, which has been developed as part of an ongoing linkage project. The MobiSoft project is driven...