paper-with-me

Papers

Fitted Q-iteration by Advantage Weighted Regression

2008-12-01 · NeurIPS 2008 12 · Gerhard Neumann, Jan R. Peters

Recently, fitted Q-iteration (FQI) based methods have become more popular due to their increased sample efficiency, a more stable learning process and the higher quality of the resulting policy. However, these methods remain hard to use for continuous action spaces which frequently occur in real-world tasks, e.g., in robotics and other technical applications. The greedy action selection commonly used for the policy improvement step is particularly problematic as it is expensive for continuous actions, can cause an unstable learning process, introduces an optimization bias and results in highly non-smooth policies unsuitable for real-world systems. In this paper, we show that by using a soft-greedy action selection the policy improvement step used in FQI can be simplified to an inexpensive advantage-weighted regression. With this result, we are able to derive a new, computationally efficient FQI algorithm which can even deal with high dimensional action spaces.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Boosted Fitted Q-Iteration

2017-08-01 · ICML 2017 8 · Samuele Tosatto, Matteo Pirotta, Carlo D’Eramo, Marcello Restelli

This paper is about the study of B-FQI, an Approximated Value Iteration (AVI) algorithm that exploits a boosting procedure to estimate the action-value function in reinforcement learning problems. B-FQI is an iterat…

regressionReinforcement Learning

Generalization Error Estimation for Primal--Dual Algorithms in Non-Smooth Regression

2026-08-14 · Kai Tan, Pierre C Bellec arxiv

This paper studies trajectory-wise estimation of generalization error for primal--dual algorithms in non-smooth regression. Motivating examples include \(\ell_1\)-penalized least absolute deviations regression and square…

Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting

2025-12-29 · Lars van der Laan, Nathan Kallus arxiv

Fitted \(Q\)-evaluation (FQE) is a standard regression-based method for off-policy evaluation, but under distribution shift, value-function realizability alone does not ensure convergence, and existing analyses often req…

Fitted Q-Iteration via Max-Plus-Linear Approximation

2024-09-12 · Y. Liu, M. A. S. Kolarijani

In this study, we consider the application of max-plus-linear approximators for Q-function in offline reinforcement learning of discounted Markov decision processes. In particular, we incorporate these approximators to p…

Soft Fitted Q-Iteration without Bellman Completeness: Occupancy Reweighting and Temperature Annealing

2025-12-30 · Lars van der Laan, Nathan Kallus arxiv

Fitted \(Q\)-iteration (FQI) is a standard regression-based method for optimal control in offline reinforcement learning, but its stability under function approximation often relies on Bellman completeness, which require…

Reinforcement Learning