English
Related papers

Related papers: Is the Bellman residual a bad proxy?

200 papers

Reinforcement learning is a framework for learning to act sequentially in an unknown environment. We propose a natural approach for modeling policy structure in policy gradients. The key idea is to optimize for a subset of future rewards:…

Machine Learning · Computer Science 2026-03-09 Puneet Mathur , Branislav Kveton , Subhojyoti Mukherjee , Viet Dac Lai

Bellman formulated a vague principle for optimization over time, which characterizes optimal policies by stating that a decision maker should not regret previous decisions retrospectively. This paper addresses time consistency in stochastic…

Optimization and Control · Mathematics 2019-06-13 Alois Pichler , Alexander Shapiro

Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with \emph{exploration} by encouraging the selection of more stochastic policies. In this work, we analyze this claim…

Machine Learning · Computer Science 2019-06-11 Zafarali Ahmed , Nicolas Le Roux , Mohammad Norouzi , Dale Schuurmans

This paper explores multiple optimization methods to improve the performance of rating-based reinforcement learning (RbRL). RbRL, a method based on the idea of human ratings, has been developed to infer reward functions in reward-free…

Machine Learning · Computer Science 2025-01-15 Evelyn Rose , Devin White , Mingkang Wu , Vernon Lawhern , Nicholas R. Waytowich , Yongcan Cao

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently…

Machine Learning · Computer Science 2019-05-15 Andreas Doerr , Michael Volpp , Marc Toussaint , Sebastian Trimpe , Christian Daniel

Reinforcement learning can greatly benefit from the use of options as a way of encoding recurring behaviours and to foster exploration. An important open problem is how can an agent autonomously learn useful options when solving particular…

Machine Learning · Computer Science 2020-01-07 Manuel Del Verme , Bruno Castro da Silva , Gianluca Baldassarre

We study the exploration problem with approximate linear action-value functions in episodic reinforcement learning under the notion of low inherent Bellman error, a condition normally employed to show convergence of approximate value…

Machine Learning · Computer Science 2020-06-30 Andrea Zanette , Alessandro Lazaric , Mykel Kochenderfer , Emma Brunskill

The success of reinforcement learning in typical settings is predicated on Markovian assumptions on the reward signal by which an agent learns optimal policies. In recent years, the use of reward machines has relaxed this assumption by…

Machine Learning · Computer Science 2022-03-29 Taylor Dohmen , Noah Topper , George Atia , Andre Beckus , Ashutosh Trivedi , Alvaro Velasquez

Inverse reinforcement learning (IRL) is the problem of finding a reward function that generates a given optimal policy for a given Markov Decision Process. This paper looks at an algorithmic-independent geometric analysis of the IRL problem…

Machine Learning · Computer Science 2021-02-19 Abi Komanduru , Jean Honorio

Reinforcement learning algorithms can show strong variation in performance between training runs with different random seeds. In this paper we explore how this affects hyperparameter optimization when the goal is to find hyperparameter…

Machine Learning · Computer Science 2020-07-31 Lars Hertel , Pierre Baldi , Daniel L. Gillen

Offline model-based optimization (MBO) seeks to discover high-performing designs using only a fixed dataset of past evaluations. Most existing methods rely on learning a surrogate model via regression and implicitly assume that good…

Machine Learning · Computer Science 2026-03-05 Shen-Huan Lyu , Rong-Xi Tan , Ke Xue , Yi-Xiao He , Yu Huang , Qingfu Zhang , Chao Qian

A recent goal in the Reinforcement Learning (RL) framework is to choose a sequence of actions or a policy to maximize the reward collected or minimize the regret incurred in a finite time horizon. For several RL problems in operation…

Machine Learning · Computer Science 2016-08-18 K J Prabuchandran , Tejas Bodas , Theja Tulabandhula

Identifying the trade-offs between model-based and model-free methods is a central question in reinforcement learning. Value-based methods offer substantial computational advantages and are sometimes just as statistically efficient as…

Machine Learning · Computer Science 2024-03-13 David Cheikhi , Daniel Russo

In many randomized experiments, the treatment effect of the long-term metric (i.e. the primary outcome of interest) is often difficult or infeasible to measure. Such long-term metrics are often slow to react to changes and sufficiently…

The theory of reinforcement learning has focused on two fundamental problems: achieving low regret, and identifying $\epsilon$-optimal policies. While a simple reduction allows one to apply a low-regret algorithm to obtain an…

Machine Learning · Computer Science 2022-06-23 Andrew Wagenmaker , Max Simchowitz , Kevin Jamieson

The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the ideal objective in RL, discounted return maximization is the…

Machine Learning · Computer Science 2025-03-19 Shuyu Yin , Fei Wen , Peilin Liu , Tao Luo

The Exploration-Exploitation tradeoff arises in Reinforcement Learning when one cannot tell if a policy is optimal. Then, there is a constant need to explore new actions instead of exploiting past experience. In practice, it is common to…

Machine Learning · Computer Science 2019-09-10 Lior Shani , Yonathan Efroni , Shie Mannor

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues…

Machine Learning · Computer Science 2020-09-15 Daoming Lyu , Qi Qi , Mohammad Ghavamzadeh , Hengshuai Yao , Tianbao Yang , Bo Liu

Stochastic resetting, where a dynamical process is intermittently returned to a fixed reference state, has emerged as a powerful mechanism for optimizing first-passage properties. Existing theory largely treats static, non-learning…

Machine Learning · Computer Science 2026-03-18 Jello Zhou , Vudtiwat Ngampruetikorn , David J. Schwab

The optimal predictor for a linear dynamical system (with hidden state and Gaussian noise) takes the form of an autoregressive linear filter, namely the Kalman filter. However, a fundamental problem in reinforcement learning and control…

Machine Learning · Computer Science 2019-05-27 Holden Lee , Cyril Zhang