English
Related papers

Related papers: Policy Optimization Through Approximate Importance…

200 papers

Experience replay is a core ingredient of modern deep reinforcement learning, yet its benefits in policy optimization are poorly understood beyond empirical heuristics. This paper develops a novel theoretical framework for experience replay…

Machine Learning · Computer Science 2026-02-04 Hua Zheng , Wei Xie , M. Ben Feng

Direct Alignment Algorithms (DAAs) such as Direct Preference Optimization (DPO) have emerged as alternatives to the standard Reinforcement Learning from Human Feedback (RLHF) for aligning large language models (LLMs) with human values.…

Machine Learning · Computer Science 2025-06-12 Phuc Minh Nguyen , Ngoc-Hieu Nguyen , Duy H. M. Nguyen , Anji Liu , An Mai , Binh T. Nguyen , Daniel Sonntag , Khoa D. Doan

We develop a new class of model-free deep reinforcement learning algorithms for data-driven, learning-based control. Our Generalized Policy Improvement algorithms combine the policy improvement guarantees of on-policy methods with the…

Machine Learning · Computer Science 2024-10-15 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

We provide performance guarantees for a variant of simulation-based policy iteration for controlling Markov decision processes that involves the use of stochastic approximation algorithms along with state-of-the-art techniques that are…

Machine Learning · Computer Science 2022-10-17 Anna Winnicki , R. Srikant

Entropy regularized algorithms such as Soft Q-learning and Soft Actor-Critic, recently showed state-of-the-art performance on a number of challenging reinforcement learning (RL) tasks. The regularized formulation modifies the standard RL…

Machine Learning · Statistics 2019-10-15 Elena Smirnova , Elvis Dohmatob

Importance sampling is a widely used technique to estimate properties of a distribution. This paper investigates trading-off some bias for variance by adaptively winsorizing the importance sampling estimator. The novel winsorizing…

Computation · Statistics 2021-02-10 Paulo Orenstein

Importance sampling (IS) is a popular technique in off-policy evaluation, which re-weights the return of trajectories in the replay buffer to boost sample efficiency. However, training with IS can be unstable and previous attempts to…

Machine Learning · Computer Science 2025-05-20 Chengyang Ying , Zhongkai Hao , Xinning Zhou , Hang Su , Dong Yan , Jun Zhu

To facilitate efficient learning, policy gradient approaches to deep reinforcement learning (RL) are typically paired with variance reduction measures and strategies for making large but safe policy changes based on a batch of experiences.…

Machine Learning · Computer Science 2023-11-13 Jared Markowitz , Edward W. Staley

Deep neural networks, when optimized with sufficient data, provide accurate representations of high-dimensional functions; in contrast, function approximation techniques that have predominated in scientific computing do not scale well with…

Data Analysis, Statistics and Probability · Physics 2021-03-15 Grant M. Rotskoff , Andrew R. Mitchell , Eric Vanden-Eijnden

Majorization-minimization algorithms consist of successively minimizing a sequence of upper bounds of the objective function. These upper bounds are tight at the current estimate, and each iteration monotonically drives the objective…

Optimization and Control · Mathematics 2015-02-03 Julien Mairal

Societies often rely on human experts to take a wide variety of decisions affecting their members, from jail-or-release decisions taken by judges and stop-and-frisk decisions taken by police officers to accept-or-reject decisions taken by…

Machine Learning · Statistics 2018-05-29 Isabel Valera , Adish Singla , Manuel Gomez Rodriguez

Learning personalized decision policies that generalize to the target population is of great relevance. Since training data is often not representative of the target population, standard policy learning methods may yield policies that do…

Machine Learning · Statistics 2021-12-03 Tobias Hatt , Daniel Tschernutter , Stefan Feuerriegel

Adaptive importance sampling is a widely spread Monte Carlo technique that uses a re-weighting strategy to iteratively estimate the so-called target distribution. A major drawback of adaptive importance sampling is the large variance of the…

Statistics Theory · Mathematics 2021-11-01 Anna Korba , François Portier

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

Machine Learning · Computer Science 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli

Adaptive importance sampling (AIS) uses past samples to update the \textit{sampling policy} $q_t$ at each stage $t$. Each stage $t$ is formed with two steps : (i) to explore the space with $n_t$ points according to $q_t$ and (ii) to exploit…

Statistics Theory · Mathematics 2018-10-04 Bernard Delyon , François Portier

This paper considers an optimization problem for a dynamical system whose evolution depends on a collection of binary decision variables. We develop scalable approximation algorithms with provable suboptimality bounds to provide…

Optimization and Control · Mathematics 2016-10-31 Insoon Yang , Samuel A. Burden , Ram Rajagopal , S. Shankar Sastry , Claire J. Tomlin

Batch policy optimization considers leveraging existing data for policy construction before interacting with an environment. Although interest in this problem has grown significantly in recent years, its theoretical foundations remain…

Machine Learning · Computer Science 2021-04-07 Chenjun Xiao , Yifan Wu , Tor Lattimore , Bo Dai , Jincheng Mei , Lihong Li , Csaba Szepesvari , Dale Schuurmans

We present a new algorithm to optimize distributions defined implicitly by parameterized stochastic diffusions. Doing so allows us to modify the outcome distribution of sampling processes by optimizing over their parameters. We introduce a…

One of the main problems of importance sampling in Bayesian networks is representation of the importance function, which should ideally be as close as possible to the posterior joint distribution. Typically, we represent an importance…

Artificial Intelligence · Computer Science 2012-07-09 Changhe Yuan , Marek J. Druzdzel

The goal of a sequential decision making problem is to design an interactive policy that adaptively selects a group of items, each selection is based on the feedback from the past, in order to maximize the expected utility of selected…

Data Structures and Algorithms · Computer Science 2022-09-13 Shaojie Tang
‹ Prev 1 3 4 5 6 7 10 Next ›