On The Convergence Of Projective-simulation-based Reinforcement Learning In Markov Decision Processes
2019 · Walter L. Boyajian, Jens Clausen, Lea M. Trenkwalder, et al.
Abstract
In recent years, the interest in leveraging quantum effects for enhancing machine learning tasks has significantly increased. Many algorithms speeding up supervised and unsupervised learning were established. The first framework in which ways to exploit quantum resources specifically for the broader context of reinforcement learning were found is projective simulation. Projective simulation presents an agent-based reinforcement learning approach designed in a manner which may support quantum walk-based speed-ups. Although classical variants of projective simulation have been benchmarked against common reinforcement learning algorithms, very few formal theoretical analyses have been provided for its performance in standard learning scenarios. In this paper, we provide a detailed formal discussion of the properties of this model. Specifically, we prove that one version of the projective simulation model, understood as a reinforcement learning approach, converges to optimal behavior in a
Authors
(none)
Tags
Stats
Related papers
- Quantum Framework For Reinforcement Learning: Integrating Markov Decision Process, Quantum Arithmetic, And Trajectory Search (2024)0.00
- Quantum Algorithms For Reinforcement Learning With A Generative Model (2021)0.00
- Quantum Policy Iteration Via Amplitude Estimation And Grover Search -- Towards Quantum Advantage For Reinforcement Learning (2022)0.00
- Quantum-enhanced Machine Learning (2016)19.33
- A Bit Of Freedom Goes A Long Way: Classical And Quantum Algorithms For Reinforcement Learning Under A Generative Model (2025)0.00
- Hybrid Quantum-classical Algorithm For Near-optimal Planning In Pomdps (2025)0.00
- Quantum Speedups In Regret Analysis Of Infinite Horizon Average-reward Markov Decision Processes (2023)0.00
- Exponential Improvements For Quantum-accessible Reinforcement Learning (2017)0.00