Arrow Research search
Back to RLDM

RLDM 2019

Reward Machines: Structuring Reward Function Specifications and Reducing Sample Complexity in Reinforcement Learning

Conference Abstract Accepted abstract Artificial Intelligence · Decision Making · Machine Learning · Reinforcement Learning

Abstract

Humans have evolved languages over thousands of years to provide useful abstractions for understanding and interacting with each other and with the physical world. Such languages include natural languages, mathematical languages and calculi, and most recently formal languages that enable us to interact with machines via human-interpretable abstractions. In this talk, I present the notion of a Reward Machine, an automata-based structure that provides a normal form representation for reward functions. Reward Ma- chines can be used natively to specify complex, non-Markovian reward-worthy behavior. Furthermore, a variety of compelling human-friendly (formal) languages can be used as reward specification languages and straightforwardly translated into Reward Machines, including variants of Linear Temporal Logic (LTL), and a variety of regular languages. Reward Machines can also be learned and can be used as memory for in- teraction in partially-observable environments. By exposing reward function structure, Reward Machines enable reward-function-tailored reinforcement learning, including tailored reward shaping and Q-learning. Experiments show that such reward-function-tailored algorithms significantly outperform state-of-the-art (deep) RL algorithms, solving problems that otherwise can’t reasonably be solved and critically reducing the sample complexity. Tuesday, July 9th, 2019

Authors

Keywords

No keywords are indexed for this paper.

Context

Venue
Multidisciplinary Conference on Reinforcement Learning and Decision Making
Archive span
2013-2025
Indexed papers
1004
Paper id
167720098540484079
v2026.09.13