English
Related papers

Related papers: On-Line Policy Iteration for Infinite Horizon Dyna…

200 papers

Off-policy learning is a framework for evaluating and optimizing policies without deploying them, from data collected by another policy. Real-world environments are typically non-stationary and the offline learned policies should adapt to…

Machine Learning · Computer Science 2021-04-06 Joey Hong , Branislav Kveton , Manzil Zaheer , Yinlam Chow , Amr Ahmed

This note introduces Isometric Policy Optimization (ISOPO), an efficient method to approximate the natural policy gradient in a single gradient step. In comparison, existing proximal policy methods such as GRPO or CISPO use multiple…

Machine Learning · Computer Science 2026-01-01 Nilin Abrahamsen

We propose a machine learning algorithm for solving finite-horizon stochastic control problems based on a deep neural network representation of the optimal policy functions. The algorithm has three features: (1) It can solve…

General Economics · Economics 2024-12-09 Xianhua Peng , Steven Kou , Lekang Zhang

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

We consider an on-line system identification setting, in which new data become available at given time steps. In order to meet real-time estimation requirements, we propose a tailored Bayesian system identification procedure, in which the…

Systems and Control · Computer Science 2016-01-19 Diego Romeres , Giulia Prando , Gianluigi Pillonetto , Alessandro Chiuso

Offline-to-online reinforcement learning (RL), by combining the benefits of offline pretraining and online finetuning, promises enhanced sample efficiency and policy performance. However, existing methods, effective as they are, suffer from…

Machine Learning · Computer Science 2023-05-26 Jianxiong Li , Xiao Hu , Haoran Xu , Jingjing Liu , Xianyuan Zhan , Ya-Qin Zhang

We propose a new method for optimistic planning in infinite-horizon discounted Markov decision processes based on the idea of adding regularization to the updates of an otherwise standard approximate value iteration procedure. This…

Machine Learning · Computer Science 2023-06-16 Antoine Moulin , Gergely Neu

Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning. By exploiting historical transitions, a policy is trained to maximize a learned value function while…

Machine Learning · Computer Science 2023-07-25 Jiachen Li , Edwin Zhang , Ming Yin , Qinxun Bai , Yu-Xiang Wang , William Yang Wang

Very recently proximal policy optimization (PPO) algorithms have been proposed as first-order optimization methods for effective reinforcement learning. While PPO is inspired by the same learning theory that justifies trust region policy…

Machine Learning · Computer Science 2018-04-20 Gang Chen , Yiming Peng , Mengjie Zhang

Optimal control problems are inherently hard to solve as the optimization must be performed simultaneously with updating the underlying system. Starting from an initial guess, Howard's policy improvement algorithm separates the step of…

Optimization and Control · Mathematics 2020-05-25 B. Kerimkulov , D. Šiška , Ł. Szpruch

We consider the problem of learning an $\varepsilon$-optimal policy in controlled dynamical systems with low-rank latent structure. For this problem, we present LoRa-PI (Low-Rank Policy Iteration), a model-free learning algorithm…

Machine Learning · Computer Science 2024-11-12 Stefan Stojanovic , Yassir Jedra , Alexandre Proutiere

We describe a nonlinear generalization of dual dynamic programming theory and its application to value function estimation for deterministic control problems over continuous state and action spaces, in a discrete-time infinite horizon…

Optimization and Control · Mathematics 2018-10-05 Joseph Warrington , Paul N. Beuchat , John Lygeros

In offline imitation learning (IL), we generally assume only a handful of expert trajectories and a supplementary offline dataset from suboptimal behaviors to learn the expert policy. While it is now common to minimize the divergence…

Machine Learning · Computer Science 2024-01-19 Hee-Jun Ahn , Seong-Woong Shim , Byung-Jun Lee

This paper presents a tutorial overview of path integral (PI) control approaches for stochastic optimal control and trajectory optimization. We concisely summarize the theoretical development of path integral control to compute a solution…

Robotics · Computer Science 2023-12-05 Muhammad Kazim , JunGee Hong , Min-Gyeom Kim , Kwang-Ki K. Kim

We present an algorithm for local, regularized, policy improvement in reinforcement learning (RL) that allows us to formulate model-based and model-free variants in a single framework. Our algorithm can be interpreted as a natural extension…

We consider the problem of planning with participation constraints introduced in [Zhang et al., 2022]. In this problem, a principal chooses actions in a Markov decision process, resulting in separate utilities for the principal and the…

Computer Science and Game Theory · Computer Science 2022-05-17 Hanrui Zhang , Yu Cheng , Vincent Conitzer

This paper proposes Partially Observable Reference Policy Programming, a novel anytime online approximate POMDP solver which samples meaningful future histories very deeply while simultaneously forcing a gradual policy update. We provide…

Artificial Intelligence · Computer Science 2025-07-17 Edward Kim , Hanna Kurniawati

The main goal of this paper is to apply the so-called policy iteration algorithm (PIA) for the long run average continuous control problem of piecewise deterministic Markov processes (PDMP's) taking values in a general Borel space and with…

Probability · Mathematics 2009-02-17 O. L. V. Costa , F. Dufour

The design of an automated vehicle controller can be generally formulated into an optimal control problem. This paper proposes a continuous-time finite-horizon approximate dynamicprogramming (ADP) method, which can synthesis off-line…

Systems and Control · Electrical Eng. & Systems 2020-07-07 Ziyu Lin , Jingliang Duan , Shengbo Eben Li , Haitong Ma , Yuming Yin

This paper studies the problem of controlling linear dynamical systems subject to point-wise-in-time constraints. We present an algorithm similar to online gradient descent, that can handle time-varying and a priori unknown convex cost…

Optimization and Control · Mathematics 2021-11-03 Marko Nonhoff , Matthias A. Müller
‹ Prev 1 8 9 10 Next ›