A Hybrid PAC Reinforcement Learning Algorithm

Abstract

This paper offers a new hybrid probably approximately correct (PAC) reinforcement learning (RL) algorithm for Markov decision processes (MDPs) that intelligently maintains favorable features of its parents. The designed algorithm, referred to as the Dyna-Delayed Q-learning (DDQ) algorithm, combines model-free and model-based learning approaches while outperforming both in most cases. The paper includes a PAC analysis of the DDQ algorithm and a derivation of its sample complexity. Numerical results are provided to support the claim regarding the new algorithm's sample efficiency compared to its parents as well as the best known model-free and model-based algorithms in application.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzehfroosh2020a

Related papers

• Hybrid Quantum-classical Algorithm For Near-optimal Planning In Pomdps (2025)0.00
• Revisiting State Augmentation Methods For Reinforcement Learning With Stochastic Delays (2021)10.35
• A Policy Gradient Primal-dual Algorithm For Constrained Mdps With Uniform PAC Guarantees (2024)0.00
• A Provably-efficient Model-free Algorithm For Constrained Markov Decision Processes (2021)0.00
• Reinforcement Learning With Delayed, Composite, And Partially Anonymous Reward (2023)0.00
• Deep Reinforcement Learning With Modulated Hebbian Plus Q Network Architecture (2019)9.76
• Multi-timescale Ensemble Q-learning For Markov Decision Process Policy Optimization (2024)6.34
• Accelerating Goal-directed Reinforcement Learning By Model Characterization (2019)2.26