English
Related papers

Related papers: Finite-Sample Analysis of the Monte Carlo Explorin…

200 papers

We investigate the problem of best policy identification in discounted linear Markov Decision Processes in the fixed confidence setting under a generative model. We first derive an instance-specific lower bound on the expected number of…

Machine Learning · Computer Science 2022-08-12 Jerome Taupin , Yassir Jedra , Alexandre Proutiere

The practicality of reinforcement learning algorithms has been limited due to poor scaling with respect to the problem size, as the sample complexity of learning an $\epsilon$-optimal policy is $\tilde{\Omega}\left(|S||A|H^3 /…

Machine Learning · Computer Science 2023-06-12 Tyler Sam , Yudong Chen , Christina Lee Yu

Least squares Monte Carlo methods are a popular numerical approximation method for solving stochastic control problems. Based on dynamic programming, their key feature is the approximation of the conditional expectation of future rewards by…

Optimization and Control · Mathematics 2022-03-28 Christian Bayer , Denis Belomestny , Paul Hager , Paolo Pigato , John Schoenmakers , Vladimir Spokoiny

Recent theoretical work studies sample-efficient reinforcement learning (RL) extensively in two settings: learning interactively in the environment (online RL), or learning from an offline dataset (offline RL). However, existing algorithms…

Machine Learning · Computer Science 2022-02-14 Tengyang Xie , Nan Jiang , Huan Wang , Caiming Xiong , Yu Bai

We investigate Monte Carlo based algorithms for solving stochastic control problems with probabilistic constraints. Our motivation comes from microgrid management, where the controller tries to optimally dispatch a diesel generator while…

Optimization and Control · Mathematics 2024-02-06 Alessandro Balata , Michael Ludkovski , Aditya Maheshwari , Jan Palczewski

Policy evaluation via Monte Carlo (MC) simulation is at the core of many MC Reinforcement Learning (RL) algorithms (e.g., policy gradient methods). In this context, the designer of the learning system specifies an interaction budget that…

Machine Learning · Computer Science 2024-10-18 Riccardo Poiani , Nicole Nobili , Alberto Maria Metelli , Marcello Restelli

Machine learning algorithms in high-dimensional settings are highly susceptible to the influence of even a small fraction of structured outliers, making robust optimization techniques essential. In particular, within the…

Machine Learning · Computer Science 2025-04-25 Changyu Gao , Andrew Lowy , Xingyu Zhou , Stephen J. Wright

We study the sample complexity of reducing reinforcement learning to a sequence of empirical risk minimization problems over the policy space. Such reductions-based algorithms exhibit local convergence in the function space, as opposed to…

Machine Learning · Computer Science 2023-01-26 Naman Agarwal , Brian Bullins , Karan Singh

Statistical inference in evolutionary models with site-dependence is a long-standing challenge in phylogenetics and computational biology. We consider the problem of approximating marginal sequence likelihoods under dependent-site models of…

Computation · Statistics 2025-11-12 Joseph Mathews , Scott C. Schmidler

We introduce \textit{Policy Guided Monte Carlo} (PGMC), a computational framework using reinforcement learning to improve Markov chain Monte Carlo (MCMC) sampling. The methodology is generally applicable, unbiased and opens up a new path to…

Computational Physics · Physics 2018-12-12 Troels Arnfred Bojesen

Binary optimization has a wide range of applications in combinatorial optimization problems such as MaxCut, MIMO detection, and MaxSAT. However, these problems are typically NP-hard due to the binary constraints. We develop a novel…

Optimization and Control · Mathematics 2023-07-04 Cheng Chen , Ruitao Chen , Tianyou Li , Ruichen Ao , Zaiwen Wen

In this note we propose a new approach towards solving numerically optimal stopping problems via reinforced regression based Monte Carlo algorithms. The main idea of the method is to reinforce standard linear regression algorithms in each…

Numerical Analysis · Mathematics 2019-07-02 Denis Belomestny , John Schoenmakers , Vladimir Spokoiny , Bakhyt Zharkynbay

We propose a gradient-free deep reinforcement learning algorithm to solve high-dimensional, finite-horizon stochastic control problems. Although the recently developed deep reinforcement learning framework has achieved great success in…

Optimization and Control · Mathematics 2025-02-03 Liyao Lyu , Jingrun Chen

We present a modular approach to reinforcement learning that uses a Bayesian representation of the uncertainty over models. The approach, BOSS (Best of Sampled Set), drives exploration by sampling multiple models from the posterior and…

Machine Learning · Computer Science 2012-05-14 John Asmuth , Lihong Li , Michael L. Littman , Ali Nouri , David Wingate

We consider the problem of learning an $\varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Given access to a generative model, we achieve rate-optimal sample…

Machine Learning · Computer Science 2024-05-13 Davide Maran , Alberto Maria Metelli , Matteo Papini , Marcello Restelli

We prove finite sample complexities for sequential Monte Carlo (SMC) algorithms which require only local mixing times of the associated Markov kernels. Our bounds are particularly useful when the target distribution is multimodal and global…

Computation · Statistics 2022-08-16 Joseph Mathews , Scott C. Schmidler

Policy optimization methods are popular reinforcement learning algorithms, because their incremental and on-policy nature makes them more stable than the value-based counterparts. However, the same properties also make them slow to converge…

Machine Learning · Computer Science 2021-07-01 Andrea Zanette , Ching-An Cheng , Alekh Agarwal

Optimal decision making with limited or no information in stochastic environments where multiple agents interact is a challenging topic in the realm of artificial intelligence. Reinforcement learning (RL) is a popular approach for arriving…

Machine Learning · Computer Science 2019-01-08 Roi Ceren

Reinforcement learning for control over continuous spaces typically uses high-entropy stochastic policies, such as Gaussian distributions, for local exploration and estimating policy gradient to optimize performance. Many robotic control…

Machine Learning · Computer Science 2024-04-03 Ya-Chien Chang , Sicun Gao

We introduce a general form of sequential Monte Carlo algorithm defined in terms of a parameterized resampling mechanism. We find that a suitably generalized notion of the Effective Sample Size (ESS), widely used to monitor algorithm…

Computation · Statistics 2016-01-08 Nick Whiteley , Anthony Lee , Kari Heine