Quantum-accessible reinforcement learning beyond strictly epochal environments

TL;DR

This paper extends quantum-accessible reinforcement learning to environments that are not strictly episodic, demonstrating that quadratic speed-ups are still achievable with minor modifications, thus broadening the scope of quantum RL applications.

Contribution

It introduces a novel framework for quantum reinforcement learning in non-episodic environments, generalizing previous models and showing the applicability of amplitude-amplification techniques.

Findings

Quadratic speed-up is achievable in non-episodic environments.

Standard amplitude-amplification techniques can be adapted for changing oracles.

The approach is proven to be optimal in certain scenarios.

Abstract

In recent years, quantum-enhanced machine learning has emerged as a particularly fruitful application of quantum algorithms, covering aspects of supervised, unsupervised and reinforcement learning. Reinforcement learning offers numerous options of how quantum theory can be applied, and is arguably the least explored, from a quantum perspective. Here, an agent explores an environment and tries to find a behavior optimizing some figure of merit. Some of the first approaches investigated settings where this exploration can be sped-up, by considering quantum analogs of classical environments, which can then be queried in superposition. If the environments have a strict periodic structure in time (i.e. are strictly episodic), such environments can be effectively converted to conventional oracles encountered in quantum information. However, in general environments, we obtain scenarios that generalize standard oracle tasks. In this work we consider one such generalization, where the environment is not strictly episodic, which is mapped to an oracle identification setting with a changing oracle. We analyze this case and show that standard amplitude-amplification techniques can, with minor modifications, still be applied to achieve quadratic speed-ups, and that this approach is optimal for certain settings. This results constitutes one of the first generalizations of quantum-accessible reinforcement learning.