← Search

Brandon Rozek

2 accepted papers

2025

A Modal Logic of Optimality (Student Abstract)

AAAI 2025technical

We present our work on a new modal logic of optimality, OPT, whose semantics are modeled in terms of optimal paths through reward-weighted transition systems. We prove some basic properties of OPT, including its status as a normal modal logic, as well as its relation to some of the standard modal ax…

Cited by 0SourcePDFScholar
2024

Partially Observable Hierarchical Reinforcement Learning with AI Planning (Student Abstract)

AAAI 2024technical

Partially observable Markov decision processes (POMDPs) challenge reinforcement learning agents due to incomplete knowledge of the environment. Even assuming monotonicity in uncertainty, it is difficult for an agent to know how and when to stop exploring for a given task. In this abstract, we discus…

Cited by 0SourcePDFScholar