Momentum Q-learning with Finite-Sample Convergence Guarantee

by   Bowen Weng, et al.

Existing studies indicate that momentum ideas in conventional optimization can be used to improve the performance of Q-learning algorithms. However, the finite-sample analysis for momentum-based Q-learning algorithms is only available for the tabular case without function approximations. This paper analyzes a class of momentum-based Q-learning algorithms with finite-sample guarantee. Specifically, we propose the MomentumQ algorithm, which integrates the Nesterov's and Polyak's momentum schemes, and generalizes the existing momentum-based Q-learning algorithms. For the infinite state-action space case, we establish the convergence guarantee for MomentumQ with linear function approximations and Markovian sampling. In particular, we characterize the finite-sample convergence rate which is provably faster than the vanilla Q-learning. This is the first finite-sample analysis for momentum-based Q-learning algorithms with function approximations. For the tabular case under synchronous sampling, we also obtain a finite-sample convergence rate that is slightly better than the SpeedyQ <cit.> when choosing a special family of step sizes. Finally, we demonstrate through various experiments that the proposed MomentumQ outperforms other momentum-based Q-learning algorithms.



There are no comments yet.


page 15


Finite-sample Analysis of Greedy-GQ with Linear Function Approximation under Markovian Noise

Greedy-GQ is an off-policy two timescale algorithm for optimal control i...

Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent

Existing convergence analyses of Q-learning mostly focus on the vanilla ...

Momentum with Variance Reduction for Nonconvex Composition Optimization

Composition optimization is widely-applied in nonconvex machine learning...

Shuffling Gradient-Based Methods with Momentum

We combine two advanced ideas widely used in optimization for machine le...

Finite-sample Efficient Conformal Prediction

Conformal prediction is a generic methodology for finite-sample valid di...

Electronic Observables for Relaxed Bilayer 2D Heterostructures in Momentum Space

We generalize the transformations and duality found in incommensurate 2D...

Finite-Sample Analysis of Stochastic Approximation Using Smooth Convex Envelopes

Stochastic Approximation (SA) is a popular approach for solving fixed po...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.