Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning

• URL: http://arxiv.org/abs/2301.00944v3
• Date: Tue, 4 Jun 2024 15:40:42 GMT
• Title: Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning
• Authors: Aritra Mitra, George J. Pappas, Hamed Hassani,
• Abstract summary: We study a variant of the classical temporal difference (TD) learning algorithm with a perturbed update direction. We prove that compressed TD algorithms, coupled with an error-feedback mechanism used widely in optimization, exhibit the same non-asymptotic approximation guarantees as their counterparts. Notably, these are the first finite-time results in RL that account for general compression operators and error-feedback in tandem with linear function approximation and Markovian sampling.
• Score: 47.904127007515925
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In large-scale distributed machine learning, recent works have studied the effects of compressing gradients in stochastic optimization to alleviate the communication bottleneck. These works have collectively revealed that stochastic gradient descent (SGD) is robust to structured perturbations such as quantization, sparsification, and delays. Perhaps surprisingly, despite the surge of interest in multi-agent reinforcement learning, almost nothing is known about the analogous question: Are common reinforcement learning (RL) algorithms also robust to similar perturbations? We investigate this question by studying a variant of the classical temporal difference (TD) learning algorithm with a perturbed update direction, where a general compression operator is used to model the perturbation. Our work makes three important technical contributions. First, we prove that compressed TD algorithms, coupled with an error-feedback mechanism used widely in optimization, exhibit the same non-asymptotic theoretical guarantees as their SGD counterparts. Second, we show that our analysis framework extends seamlessly to nonlinear stochastic approximation schemes that subsume Q-learning. Third, we prove that for multi-agent TD learning, one can achieve linear convergence speedups with respect to the number of agents while communicating just $\tilde{O}(1)$ bits per iteration. Notably, these are the first finite-time results in RL that account for general compression operators and error-feedback in tandem with linear function approximation and Markovian sampling. Our proofs hinge on the construction of novel Lyapunov functions that capture the dynamics of a memory variable introduced by error-feedback.

Related papers

• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression [53.15502562048627]
  Recent work has built the connection between self-supervised learning and the approximation of the top eigenspace of a graph Laplacian operator. This work delves into a statistical analysis of augmentation-based pretraining.
  arXiv  Detail & Related papers  (2023-06-01T15:18:55Z)
• Koopman Kernel Regression [6.116741319526748]
  We show that Koopman operator theory offers a beneficial paradigm for characterizing forecasts via linear time-invariant (LTI) ODEs. We derive a universal Koopman-invariant kernel reproducing Hilbert space (RKHS) that solely spans transformations into LTI dynamical systems. Our experiments demonstrate superior forecasting performance compared to Koopman operator and sequential data predictors.
  arXiv  Detail & Related papers  (2023-05-25T16:22:22Z)
• Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning [53.17258888552998]
  This work proposes an exploration variant of the basic $Q$-learning protocol with linear function approximation. We show that the performance of the algorithm degrades very gracefully under a novel and more permissive notion of approximation error.
  arXiv  Detail & Related papers  (2022-06-01T23:26:51Z)
• Simple Stochastic and Online Gradient DescentAlgorithms for Pairwise Learning [65.54757265434465]
  Pairwise learning refers to learning tasks where the loss function depends on a pair instances. Online descent (OGD) is a popular approach to handle streaming data in pairwise learning. In this paper, we propose simple and online descent to methods for pairwise learning.
  arXiv  Detail & Related papers  (2021-11-23T18:10:48Z)
• Compressing gradients by exploiting temporal correlation in momentum-SGD [17.995905582226463]
  We analyze compression methods that exploit temporal correlation in systems with and without error-feedback. Experiments with the ImageNet dataset demonstrate that our proposed methods offer significant reduction in the rate of communication. We prove the convergence of SGD under an expected error assumption by establishing a bound for the minimum gradient norm.
  arXiv  Detail & Related papers  (2021-08-17T18:04:06Z)
• A Stable High-order Tuner for General Convex Functions [0.0]
  High-order Tuner (HT) was developed for linear regression problems. In this paper, we extend and discuss the results of this same HT for general convex loss functions. We provide numerical simulations supporting the satisfactory behavior of the HT algorithm as well as an accelerated learning property.
  arXiv  Detail & Related papers  (2020-11-19T17:50:53Z)
• Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks [50.42141893913188]
  We study a distributed variable for large-scale AUC for a neural network as with a deep neural network. Our model requires a much less number of communication rounds and still a number of communication rounds in theory. Our experiments on several datasets show the effectiveness of our theory and also confirm our theory.
  arXiv  Detail & Related papers  (2020-05-05T18:08:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.