no code implementations • 8 Aug 2022 • Daniel T. Larsson, Dipankar Maity, Panagiotis Tsiotras
It is shown that the resulting information-theoretic abstraction problem over the space of multi-resolution trees can be formulated as a integer linear programming (ILP) problem.
no code implementations • 19 Feb 2021 • Daniel T. Larsson, Dipankar Maity, Panagiotis Tsiotras
In this paper, a mixed-integer linear programming formulation for the problem of obtaining task-relevant, multi-resolution, graph abstractions for resource-constrained agents is presented.
no code implementations • 19 May 2020 • Daniel T. Larsson, Dipankar Maity, Panagiotis Tsiotras
In this paper, we develop a framework for path-planning on abstractions that are not provided to the agent a priori but instead emerge as a function of the available computational resources.
no code implementations • 30 Sep 2019 • Daniel T. Larsson, Dipankar Maity, Panagiotis Tsiotras
In this paper, we develop a framework to obtain graph abstractions for decision-making by an agent where the abstractions emerge as a function of the agent's limited computational resources.
no code implementations • 22 Oct 2017 • Daniel T. Larsson, Daniel Braun, Panagiotis Tsiotras
In this semi-tutorial paper, we first review the information-theoretic approach to account for the computational costs incurred during the search for optimal actions in a sequential decision-making problem.