Papers › Using Reward Machines for High-Level Task Specification and Decomposition in...

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

1 Jul 2018ICML 2018 7archive 2025-07-28

Rodrigo Toro Icarte, Toryn Klassen, Richard Valenzano, Sheila Mcilraith

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 decomposes the reward machine and uses off-policy q-learning to simultaneously learn subpolicies for the different components. QRM is guaranteed to converge to an optimal policy in the tabular case, in contrast to Hierarchical Reinforcement Learning methods which might converge to suboptimal policies. We demonstrate this behavior experimentally in two discrete domains. We also show how function approximation methods like neural networks can be incorporated into QRM, and that doing so can find better policies more quickly than hierarchical methods in a domain with a continuous state space.

PaperPDFCode

Code

bitbucket.org/RToroIcarte/qrm officialmentioned in papertf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Hierarchical Reinforcement LearningQ-LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Q-Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections