Joint inference of reward machines and policies for reinforcement learning

Zhe Xu, Ivan Gavran, Yousef Ahmad, Rupak Majumdar, Daniel Neider, Ufuk Topcu, Bo Wu

Research output: Contribution to journalConference articlepeer-review

37 Scopus citations


Incorporating high-level knowledge is an effective way to expedite reinforcement learning (RL), especially for complex tasks with sparse rewards. We investigate an RL problem where the high-level knowledge is in the form of reward machines, a type of Mealy machines that encode non-Markovian reward functions. We focus on a setting in which this knowledge is a priori not available to the learning agent. We develop an iterative algorithm that performs joint inference of reward machines and policies for RL (more specifically, q-learning). In each iteration, the algorithm maintains a hypothesis reward machine and a sample of RL episodes. It uses a separate q-function defined for each state of the current hypothesis reward machine to determine the policy and performs RL to update the q-functions. While performing RL, the algorithm updates the sample by adding RL episodes along which the obtained rewards are inconsistent with the rewards based on the current hypothesis reward machine. In the next iteration, the algorithm infers a new hypothesis reward machine from the updated sample. Based on an equivalence relation between states of reward machines, we transfer the q-functions between the hypothesis reward machines in consecutive iterations. We prove that the proposed algorithm converges almost surely to an optimal policy in the limit. The experiments show that learning high-level knowledge in the form of reward machines leads to fast convergence to optimal policies in RL, while the baseline RL methods fail to converge to optimal policies after a substantial number of training steps.

Original languageEnglish (US)
Pages (from-to)590-598
Number of pages9
JournalProceedings International Conference on Automated Planning and Scheduling, ICAPS
StatePublished - May 29 2020
Externally publishedYes
Event30th International Conference on Automated Planning and Scheduling, ICAPS 2020 - Nancy, France
Duration: Oct 26 2020Oct 30 2020

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Information Systems and Management


Dive into the research topics of 'Joint inference of reward machines and policies for reinforcement learning'. Together they form a unique fingerprint.

Cite this