English
Related papers

Related papers: A Single Deep Preference-Conditioned Policy for Le…

200 papers

Modern policy optimization methods roughly follow the policy mirror descent (PMD) algorithmic template, for which there are by now numerous theoretical convergence results. However, most of these either target tabular environments, or can…

Machine Learning · Computer Science 2025-07-08 Uri Sherman , Tomer Koren , Yishay Mansour

We address the problem of finding the optimal policy of a constrained Markov decision process (CMDP) using a gradient descent-based algorithm. Previous results have shown that a primal-dual approach can achieve an $\mathcal{O}(1/\sqrt{T})$…

Machine Learning · Computer Science 2022-02-07 Tao Liu , Ruida Zhou , Dileep Kalathil , P. R. Kumar , Chao Tian

Policy Mirror Descent (PMD) is a general family of algorithms that covers a wide range of novel and fundamental methods in reinforcement learning. Motivated by the instability of policy iteration (PI) with inexact policy evaluation, PMD…

Optimization and Control · Mathematics 2023-11-23 Emmeran Johnson , Ciara Pike-Burke , Patrick Rebeschini

It is desirable in many multi-objective machine learning applications, such as multi-task learning with conflicting objectives and multi-objective reinforcement learning, to find a Pareto solution that can match a given preference of a…

Machine Learning · Computer Science 2024-02-19 Xiaoyuan Zhang , Xi Lin , Qingfu Zhang

Learning from Preferential Feedback (LfPF) plays an essential role in training Large Language Models, as well as certain types of interactive learning agents. However, a substantial gap exists between the theory and application of LfPF…

Machine Learning · Computer Science 2024-03-29 Jonathan Colaço Carr , Prakash Panangaden , Doina Precup

Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations. In reinforcement learning, a set of diverse policies can be useful for exploration, transfer,…

Artificial Intelligence · Computer Science 2022-01-05 Tom Zahavy , Brendan O'Donoghue , Andre Barreto , Volodymyr Mnih , Sebastian Flennerhag , Satinder Singh

We consider the problem of learning the optimal policy for infinite-horizon Markov decision processes (MDPs). For this purpose, some variant of Stochastic Mirror Descent is proposed for convex programming problems with Lipschitz-continuous…

Optimization and Control · Mathematics 2022-03-01 Daniil Tiapkin , Alexander Gasnikov

We consider the problem of learning an $\varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Given access to a generative model, we achieve rate-optimal sample…

Machine Learning · Computer Science 2024-05-13 Davide Maran , Alberto Maria Metelli , Matteo Papini , Marcello Restelli

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…

Machine Learning · Computer Science 2014-08-12 Aristide Tossou , Christos Dimitrakakis

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…

Machine Learning · Statistics 2013-07-16 Aristide C. Y. Tossou , Christos Dimitrakakis

Continual learning aims to learn multiple tasks sequentially. A key challenge in continual learning is balancing between two objectives: retaining knowledge from old tasks (stability) and adapting to new tasks (plasticity). Experience…

Machine Learning · Computer Science 2025-04-01 Song Lai , Zhe Zhao , Fei Zhu , Xi Lin , Qingfu Zhang , Gaofeng Meng

This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in…

Machine Learning · Computer Science 2020-08-26 Lingwei Zhu , Takamitsu Matsubara

This paper studies the policy mirror descent (PMD) method, which is a general policy optimization framework in reinforcement learning and can cover a wide range of policy gradient methods by specifying difference mirror maps. Existing…

Optimization and Control · Mathematics 2026-01-01 Wenye Li , Hongxu Chen , Jiacai Liu , Ke Wei

Many real-world problems require trading off multiple competing objectives. However, these objectives are often in different units and/or scales, which can make it challenging for practitioners to express numerical preferences over…

Markov decision processes (MDPs) are a popular model for performance analysis and optimization of stochastic systems. The parameters of stochastic behavior of MDPs are estimates from empirical observations of a system; their values are not…

Artificial Intelligence · Computer Science 2017-10-26 Dimitri Scheftelowitsch , Peter Buchholz , Vahid Hashemi , Holger Hermanns

We consider the problem of solving robust Markov decision process (MDP), which involves a set of discounted, finite state, finite action space MDPs with uncertain transition kernels. The goal of planning is to find a robust policy that…

Machine Learning · Computer Science 2023-06-13 Yan Li , Guanghui Lan , Tuo Zhao

Prior work in multi-objective reinforcement learning typically uses linear reward scalarization with fixed weights, which provably fails to capture non-convex Pareto fronts and thus yields suboptimal results. This limitation becomes…

Machine Learning · Computer Science 2026-04-01 Yining Lu , Zilong Wang , Shiyang Li , Xin Liu , Changlong Yu , Qingyu Yin , Zhan Shi , Zixuan Zhang , Meng Jiang

We study the $(\varepsilon, \delta)$-PAC policy identification problem in finite-horizon episodic Markov Decision Processes. Existing approaches provide finite-time guarantees for approximate settings ($\varepsilon>0$) but suffer from high…

Machine Learning · Computer Science 2026-05-06 Cyrille Kone , Kevin Jamieson

We study model-based learning of finite-window policies in tabular partially observable Markov decision processes (POMDPs). A common approach to learning under partial observability is to approximate unbounded history dependencies using…

Machine Learning · Computer Science 2026-04-02 Philip Jordan , Maryam Kamgarpour

Direct Preference Optimization (DPO) has become a popular approach for aligning language models using pairwise preferences. However, in practical post-training pipelines, on-policy generation typically yields multiple candidate responses…

Machine Learning · Computer Science 2025-06-23 Taneesh Gupta , Rahul Madhavan , Xuchao Zhang , Nagarajan Natarajan , Chetan Bansal , Saravan Rajmohan