We study decision-theoretic planning or reinforcement learning in the presence of traps such as steep slopes for outdoor robots or staircases for indoor robots. In this case, achi...
In real world applications, agents - be they software agents or autonomous robots - inevitably face erroneous situations that have not been planned for. Re-planning can sometimes ...
Robert J. Ross, Rem W. Collier, Gregory M. P. O'Ha...
High-level controllers that operate robots in dynamic, uncertain domains are concerned with at least two reasoning tasks dealing with the effects of noisy sensors and effectors: T...
: This paper presents a method called "Situation Matching" that aids to improve cooperative tasks in heterogeneous multi-agent systems. The situation matching (SM) above ...
Goal-directed Markov Decision Process models (GDMDPs) are good models for many decision-theoretic planning tasks. They have been used in conjunction with two different reward stru...