Framework for learning agents in quantum environments

Published

September 22, 2016

Author(s)

Jacob M. Taylor, Hans Briegel, Vedran Dunjko

Abstract

In this paper we provide a broad framework for describing learning agents in general quantum environments. We analyze the types of environments which allow for quantum enhancements in learning, by contrasting environments to quantum oracles. We show that whether or not quantum improvements are at all possible depends on the internal structure of the quantum environment. If the environments are constructed and the internal structure is appropriately chosen, or if the agent has limited capacities to influence the internal states of the environment, we show that improvements in learning times are possible in a broad range of scenarios. Such scenarios we call luck-favoring settings. The case of constructed environments is particularly relevant for the class of model-based learning agents, where our results imply a near-generic improvement.

Citation

Physical Review Letters

Volume

117

Pub Type

Journals

Download Paper

DOI Link

Keywords

Quantum Computation, Machine Learning, Quantum Information

Citation

Taylor, J. , Briegel, H. and Dunjko, V. (2016), Framework for learning agents in quantum environments, Physical Review Letters, [online], https://doi.org/10.1103/PhysRevLett.117.130501 (Accessed April 25, 2025)