Finite-time Performance Bounds And Adaptive Learning Rate Selection For Two Time-scale Reinforcement Learning

Abstract

We study two time-scale linear stochastic approximation algorithms, which can be used to model well-known reinforcement learning algorithms such as GTD, GTD2, and TDC. We present finite-time performance bounds for the case where the learning rate is fixed. The key idea in obtaining these bounds is to use a Lyapunov function motivated by singular perturbation theory for linear differential equations. We use the bound to design an adaptive learning rate scheme which significantly improves the convergence rate over the known optimal polynomial decay rule in our experiments, and can be used to potentially improve the performance of any other schedule where the learning rate is changed at pre-determined time instants.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygupta2019finite

Related papers

• A Tale Of Two-timescale Reinforcement Learning With The Tightest Finite-time Bound (2019)0.00
• Finite Sample Analysis Of Two-timescale Stochastic Approximation With Applications To Reinforcement Learning (2017)0.00
• Sample Complexity Bounds For Two Timescale Value-based Reinforcement Learning Algorithms (2020)0.00
• Two Time-scale Off-policy TD Learning: Non-asymptotic Analysis Over Markovian Samples (2019)0.00
• Non-asymptotic Analysis For Two Time-scale TDC With General Smooth Function Approximation (2021)0.00
• Central Limit Theorem For Two-timescale Stochastic Approximation With Markovian Noise: Theory And Applications (2024)0.00
• Adaptive Temporal Difference Learning With Linear Function Approximation (2020)0.00
• Fast Two-time-scale Stochastic Gradient Method With Applications In Reinforcement Learning (2024)0.00