paper-with-me

Papers

Asynchronous stochastic approximations with asymptotically biased errors and deep multi-agent learning

2018-02-22 · Arunselvan Ramaswamy, Shalabh Bhatnagar, Daniel E. Quevedo

Asynchronous stochastic approximations (SAs) are an important class of model-free algorithms, tools and techniques that are popular in multi-agent and distributed control scenarios. To counter Bellman's curse of dimensionality, such algorithms are coupled with function approximations. Although the learning/ control problem becomes more tractable, function approximations affect stability and convergence. In this paper, we present verifiable sufficient conditions for stability and convergence of asynchronous SAs with biased approximation errors. The theory developed herein is used to analyze Policy Gradient methods and noisy Value Iteration schemes. Specifically, we analyze the asynchronous approximate counterparts of the policy gradient (A2PG) and value iteration (A2VI) schemes. It is shown that the stability of these algorithms is unaffected by biased approximation errors, provided they are asymptotically bounded. With respect to convergence (of A2VI and A2PG), a relationship between the limiting set and the approximation errors is established. Finally, experimental results are presented that support the theory.

📄 PDF Abstract BibTeX arXiv:1802.07935

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement LearningPolicy Gradient Methods

Similar Papers 제목 키워드 기반

Bounding Wasserstein distance with couplings

2021-12-06 · pproximateinference AABI Symposium 2022 2 · Niloy Biswas, Lester Mackey

Markov chain Monte Carlo (MCMC) provides asymptotically consistent estimates of intractable posterior expectations as the number of iterations tends to infinity. However, in large data applications, MCMC can be computati…

regression

Asynchronous stochastic convex optimization

2015-08-04 · John C. Duchi, Sorathan Chaturapruek, Christopher Ré

We show that asymptotically, completely asynchronous stochastic gradient procedures achieve optimal (even to constant factors) convergence rates for the solution of convex optimization problems under nearly the same cond…

Stochastic Optimization

Asynchronous stochastic convex optimization: the noise is in the noise and SGD don't care

2015-12-01 · NeurIPS 2015 12 · Sorathan Chaturapruek, John C. Duchi, Christopher Ré

We show that asymptotically, completely asynchronous stochastic gradient procedures achieve optimal (even to constant factors) convergence rates for the solution of convex optimization problems under nearly the same cond…

Stochastic Optimization

Analyzing Approximate Value Iteration Algorithms

2017-09-14 · Arunselvan Ramaswamy, Shalabh Bhatnagar

In this paper, we consider the stochastic iterative counterpart of the value iteration scheme wherein only noisy and possibly biased approximations of the Bellman operator are available. We call this counterpart as the a…

Stochastic Approximation with Biased MCMC for Expectation Maximization

2024-02-27 · Samuel Gruffaz, Kyurae Kim, Alain Oliviero Durmus, Jacob R. Gardner

The expectation maximization (EM) algorithm is a widespread method for empirical Bayesian inference, but its expectation step (E-step) is often intractable. Employing a stochastic approximation scheme with Markov chain M…

Bayesian Inference