3 papers
math.OC2026
On Partial Optimality in QUBO via Quadratic Posiform Autarkies
Lucas Fabian Naumann, Bjoern Andres
Partially optimal assignments (also called persistencies) allow combinatorial optimization problems to be reduced by fixing a subset of variables to values consistent with at least…
cs.LG2024
Provably Efficient Exploration in Reward Machines with Low Regret
Hippolyte Bourel, Anders Jonsson, Odalric-Ambrym Maillard +2
We study reinforcement learning (RL) for decision processes with non-Markovian reward, in which high-level knowledge of the task in the form of reward machines is available to the…
cs.LG2024
Tractable Offline Learning of Regular Decision Processes
Ahana Deb, Roberto Cipollone, Anders Jonsson +2
This work studies offline Reinforcement Learning (RL) in a class of non-Markovian environments called Regular Decision Processes (RDPs). In RDPs, the unknown dependency of future o…