English
Related papers

Related papers: Provable and Practical: Efficient Exploration in R…

200 papers

Recent advancements in deep reinforcement learning (RL) have demonstrated notable progress in sample efficiency, spanning both model-based and model-free paradigms. Despite the identification and mitigation of specific bottlenecks in prior…

Machine Learning · Computer Science 2024-04-02 Yibo Wang , Jiang Zhao

We explore a self-learning Markov chain Monte Carlo method based on the Adversarial Non-linear Independent Components Estimation Monte Carlo, which utilizes generative models and artificial neural networks. We apply this method to the…

Disordered Systems and Neural Networks · Physics 2021-01-06 Matija Medvidovic , Juan Carrasquilla , Lauren E. Hayward , Bohdan Kulchytskyy

Partially Observable Markov Decision Processes (POMDPs) can model complex sequential decision-making problems under stochastic and uncertain environments. A main reason hindering their broad adoption in real-world applications is the lack…

For the problem of task-agnostic reinforcement learning (RL), an agent first collects samples from an unknown environment without the supervision of reward signals, then is revealed with a reward and is asked to compute a corresponding…

Machine Learning · Computer Science 2022-03-16 Jingfeng Wu , Vladimir Braverman , Lin F. Yang

We study a posterior sampling approach to efficient exploration in constrained reinforcement learning. Alternatively to existing algorithms, we propose two simple algorithms that are more efficient statistically, simpler to implement and…

Machine Learning · Computer Science 2022-09-09 Danil Provodin , Pratik Gajane , Mykola Pechenizkiy , Maurits Kaptein

Although model-based reinforcement learning (RL) approaches are considered more sample efficient, existing algorithms are usually relying on sophisticated planning algorithm to couple tightly with the model-learning procedure. Hence the…

Machine Learning · Computer Science 2022-03-15 Xiaoyu Chen , Jiachen Hu , Lin F. Yang , Liwei Wang

Monte Carlo (MC) integration is the de facto method for approximating the predictive distribution of Bayesian neural networks (BNNs). But, even with many MC samples, Gaussian-based BNNs could still yield bad predictive performance due to…

Machine Learning · Computer Science 2022-10-18 Agustinus Kristiadi , Runa Eschenhagen , Philipp Hennig

Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on…

Machine Learning · Computer Science 2021-09-29 Hamed Khorasgani , Haiyan Wang , Chetan Gupta , Susumu Serita

Model-based reinforcement learning (RL) methods that leverage search are responsible for many milestone breakthroughs in RL. Sequential Monte Carlo (SMC) recently emerged as an alternative to the Monte Carlo Tree Search (MCTS) algorithm…

Machine Learning · Computer Science 2026-05-22 Yaniv Oren , Joery A. de Vries , Pascal R. van der Vaart , Matthijs T. J. Spaan , Wendelin Böhmer

This paper is concerned with offline reinforcement learning (RL), which learns using pre-collected data without further exploration. Effective offline RL would be able to accommodate distribution shift and limited data coverage. However,…

Machine Learning · Statistics 2024-03-11 Gen Li , Laixi Shi , Yuxin Chen , Yuejie Chi , Yuting Wei

Deep reinforcement learning (DRL) faces significant challenges in addressing the hard-exploration problems in tasks with sparse or deceptive rewards and large state spaces. These challenges severely limit the practical application of DRL.…

Machine Learning · Computer Science 2024-01-03 Guojian Wang , Faguo Wu , Xiao Zhang , Ning Guo , Zhiming Zheng

In parameter estimation problems one computes a posterior distribution over uncertain parameters defined jointly by a prior distribution, a model, and noisy data. Markov Chain Monte Carlo (MCMC) is often used for the numerical solution of…

Numerical Analysis · Mathematics 2017-11-15 Matthias Morzfeld , Marcus S. Day , Ray W. Grout , George Shu Heng Pau , Stefan A. Finsterle , John B. Bell

This paper presents a new Metropolis-adjusted Langevin algorithm (MALA) that uses convex analysis to simulate efficiently from high-dimensional densities that are log-concave, a class of probability distributions that is widely used in…

Methodology · Statistics 2015-04-06 Marcelo Pereyra

Langevin Monte Carlo (LMC) is an iterative algorithm used to generate samples from a distribution that is known only up to a normalizing constant. The nonasymptotic dependence of its mixing time on the dimension and target accuracy is…

Machine Learning · Statistics 2020-02-26 Niladri S. Chatterji , Jelena Diakonikolas , Michael I. Jordan , Peter L. Bartlett

Hamiltonian Monte Carlo is a widely used algorithm for sampling from posterior distributions of complex Bayesian models. It can efficiently explore high-dimensional parameter spaces guided by simulated Hamiltonian flows. However, the…

Computation · Statistics 2019-04-29 Lingge Li , Andrew Holbrook , Babak Shahbaba , Pierre Baldi

We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and unified proofs of convergence for a variety of…

Machine Learning · Computer Science 2020-03-30 Philip Amortila , Doina Precup , Prakash Panangaden , Marc G. Bellemare

Most successful applications of deep learning involve similar training and test conditions. However, tasks such as biological sequence design involve searching for sequences that improve desirable properties beyond previously known values,…

Machine Learning · Computer Science 2025-05-27 Sophia Hager , Aleem Khan , Andrew Wang , Nicholas Andrews

Reward-free reinforcement learning (RL) considers the setting where the agent does not have access to a reward function during exploration, but must propose a near-optimal policy for an arbitrary reward function revealed only after…

Machine Learning · Computer Science 2022-06-22 Andrew Wagenmaker , Yifang Chen , Max Simchowitz , Simon S. Du , Kevin Jamieson

Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging due to intractable sequence-level likelihoods. Existing…

We construct a new framework for accelerating Markov chain Monte Carlo in posterior sampling problems where standard methods are limited by the computational cost of the likelihood, or of numerical models embedded therein. Our approach…

Methodology · Statistics 2017-01-06 Patrick R. Conrad , Youssef M. Marzouk , Natesh S. Pillai , Aaron Smith