Advances in Quantum Reinforcement Learning

Abstract

In recent times, there has been much interest in quantum enhancements of machine learning, specifically in the context of data mining and analysis. Reinforcement learning, an interactive form of learning, is, in turn, vital in artificial intelligence-type applications. Also in this case, quantum mechanics was shown to be useful, in certain instances. Here, we elucidate these results, and show that quantum enhancements can be achieved in a new setting: the setting of learning models which learn how to improve themselves -- that is, those that meta-learn. While not all learning models meta-learn, all non-trivial models have the potential of being "lifted", enhanced, to meta-learning models. Our results show that also such models can be quantum-enhanced to make even better learners. In parallel, we address one of the bottlenecks of current quantum reinforcement learning approaches: the need for so-called oracularized variants of task environments. Here we elaborate on a method which realizes these variants, with minimal changes in the setting, and with no corruption of the operative specification of the environments. This result may be important in near-term experimental demonstrations of quantum reinforcement learning.

arXiv comment6 pages, 2 figures. Presented at IEEE SMC in 2017. Introduction overlaps in part with arXiv:1507.08482

References in corpus (12)

• Quantum support vector machine for big data classification
• Quantum Amplitude Amplification and Estimation
• Quantum random access memory
• Quantum algorithms for supervised and unsupervised machine learning
• Quantum-enhanced machine learning
• Quantum Circuits Architecture
• A Quantum Algorithm for Finding the Minimum
• Prediction by linear regression on a quantum computer
• Quantum speedup for active learning agents
• Fast quantum algorithm for numerical gradient estimation
• Meta-learning within Projective Simulation
• Framework for learning agents in quantum environments

Cited by in corpus (16)

• The prospects of quantum computing in computational molecular biology
• Quantum agents in the Gym: a variational quantum algorithm for deep Q-learning
• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• Quantum Natural Language Processing on Near-Term Quantum Computers
• Training Optimization for Gate-Model Quantum Neural Networks
• Quantum Machine Learning for Finance
• Self-Correcting Quantum Many-Body Control using Reinforcement Learning with Tensor Networks
• ResQNets: A Residual Approach for Mitigating Barren Plateaus in Quantum Neural Networks
• Quantum Deep Reinforcement Learning for Robot Navigation Tasks
• Benchmarking projective simulation in navigation problems
• Quantum reinforcement learning in continuous action space
• Quantum exploration algorithms for multi-armed bandits
• Quantum Algorithms for Reinforcement Learning with a Generative Model
• Quantum-accessible reinforcement learning beyond strictly epochal environments
• Hybrid quantum-classical unsupervised data clustering based on the self-organizing feature map
• Policy Gradients using Variational Quantum Circuits