← Search

Toryn Klassen

2 accepted papers

2019

Learning Reward Machines for Partially Observable Reinforcement Learning

NeurIPS 2019spotlight

Reward Machines (RMs), originally proposed for specifying problems in Reinforcement Learning (RL), provide a structured, automata-based representation of a reward function that allows an agent to decompose problems into subproblems that can be efficiently learned using off-policy learning. Here we s…

2018

Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning

ICML 2018oral

In this paper we propose Reward Machines {—} a type of finite state machine that supports the specification of reward functions while exposing reward function structure to the learner and supporting decomposition. We then present Q-Learning for Reward Machines (QRM), an algorithm which appropriately…