English
Related papers

Related papers: A Unified Approach for Multi-step Temporal-Differe…

200 papers

In this paper, a novel Q-learning scheduling method for the current controller of switched reluctance motor (SRM) drive is investigated. Q-learning algorithm is a class of reinforcement learning approaches that can find the best…

Systems and Control · Electrical Eng. & Systems 2020-06-16 Hamad A. Alharkan , Sepehr Saadatmand , Mehdi Ferdowsi , Pourya Shamsi

The famous Policy Iteration algorithm alternates between policy improvement and policy evaluation. Implementations of this algorithm with several variants of the latter evaluation stage, e.g, $n$-step and trace-based returns, have been…

Artificial Intelligence · Computer Science 2018-08-01 Yonathan Efroni , Gal Dalal , Bruno Scherrer , Shie Mannor

Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval quality in isolation without accounting for the dependency chains through which…

Artificial Intelligence · Computer Science 2026-05-15 Junwei Liao , Haoting Shi , Ruiwen Zhou , Jiaqian Wang , Shengtao Zhang , Wei Zhang , Ying Wen , Zhiyu Li , Feiyu Xiong , Bo Tang , Weinan Zhang , Muning Wen

Unmanned Aerial Vehicles need an online path planning capability to move in high-risk missions in unknown and complex environments to complete them safely. However, many algorithms reported in the literature may not return reliable…

In this work, we take a fresh look at some old and new algorithms for off-policy, return-based reinforcement learning. Expressing these in a common form, we derive a novel algorithm, Retrace($\lambda$), with three desired properties: (1) it…

Machine Learning · Computer Science 2016-11-09 Rémi Munos , Tom Stepleton , Anna Harutyunyan , Marc G. Bellemare

Off-policy, value-based reinforcement learning methods such as Q-learning are appealing because they can learn from arbitrary experience, including data collected by older policies or other agents. In practice, however, bootstrapping makes…

Artificial Intelligence · Computer Science 2026-05-12 Armaan A. Abraham , Lucy Xiaoyang Shi , Chelsea Finn

Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning. Traditional methods consider these two problems as independent, resulting in a classical two-stage paradigm: first learn…

Artificial Intelligence · Computer Science 2019-11-25 Tianyu Li , Bogdan Mazoure , Doina Precup , Guillaume Rabusseau

In recent work it is shown that Q-learning with linear function approximation is stable, in the sense of bounded parameter estimates, under the $(\varepsilon,\kappa)$-tamed Gibbs policy; $\kappa$ is inverse temperature, and $\varepsilon>0$…

Machine Learning · Computer Science 2026-02-09 Prashant Mehta , Sean Meyn

Achieving fast and stable off-policy learning in deep reinforcement learning (RL) is challenging. Most existing methods rely on semi-gradient temporal-difference (TD) methods for their simplicity and efficiency, but are consequently…

Machine Learning · Computer Science 2025-09-22 Esraa Elelimy , Brett Daley , Andrew Patterson , Marlos C. Machado , Adam White , Martha White

$Q$-learning with function approximation is one of the most popular methods in reinforcement learning. Though the idea of using function approximation was proposed at least 60 years ago, even in the simplest setup, i.e, approximating…

Machine Learning · Computer Science 2019-11-05 Simon S. Du , Yuping Luo , Ruosong Wang , Hanrui Zhang

Off-policy reinforcement learning of pretrained flow policies remains challenging due to the instability of optimization arising from the multi-step sampling process. Recently, Q-learning with Adjoint Matching (QAM) addressed this issue by…

Machine Learning · Computer Science 2026-05-27 Yonghoon Dong , Kyungmin Lee , Changyeon Kim , Jaehyuk Kim , Jinwoo Shin

We introduce a variant of Multicut Decomposition Algorithms (MuDA), called CuSMuDA (Cut Selection for Multicut Decomposition Algorithms), for solving multistage stochastic linear programs that incorporates a class of cut selection…

Optimization and Control · Mathematics 2019-07-23 Vincent Guigues , Michelle Bandarra

The temporal-difference methods TD($\lambda$) and Sarsa($\lambda$) form a core part of modern reinforcement learning. Their appeal comes from their good performance, low computational cost, and their simple interpretation, given by their…

Artificial Intelligence · Computer Science 2016-09-09 Harm van Seijen , A. Rupam Mahmood , Patrick M. Pilarski , Marlos C. Machado , Richard S. Sutton

This paper presents a model-free reinforcement learning (RL) algorithm to synthesize a control policy that maximizes the satisfaction probability of linear temporal logic (LTL) specifications. Due to the consideration of environment and…

Formal Languages and Automata Theory · Computer Science 2022-01-04 Mingyu Cai , Shaoping Xiao , Baoluo Li , Zhiliang Li , Zhen Kan

In state of the art model-free off-policy deep reinforcement learning, a replay memory is used to store past experience and derive all network updates. Even if both state and action spaces are continuous, the replay memory only holds a…

Machine Learning · Computer Science 2020-07-16 Sabrina Hoppe , Marc Toussaint

We develop a continuous-time reinforcement learning framework for a class of singular stochastic control problems without entropy regularization. The optimal singular control is characterized as the optimal singular control law, which is a…

Optimization and Control · Mathematics 2026-05-14 Zongxia Liang , Xiaodong Luo , Xiang Yu

Meta-learning methods aim to build learning algorithms capable of quickly adapting to new tasks in low-data regime. One of the most difficult benchmarks of such algorithms is a one-shot learning problem. In this setting many algorithms face…

Machine Learning · Computer Science 2022-10-04 Andrei Boiarov , Kostiantyn Khabarlak , Igor Yastrebov

Q-learning is known as one of the fundamental reinforcement learning (RL) algorithms. Its convergence has been the focus of extensive research over the past several decades. Recently, a new finitetime error bound and analysis for Q-learning…

Systems and Control · Electrical Eng. & Systems 2024-01-17 Donghwna Lee

This dissertation makes three main contributions. First, We identify a new connection between policy gradient and dynamic programming in MMDPs and propose the Coordinate Ascent Dynamic Programming (CADP) algorithm to compute a Markov policy…

Machine Learning · Computer Science 2025-10-21 Xihong Su

Deep reinforcement learning for high dimensional, hierarchical control tasks usually requires the use of complex neural networks as functional approximators, which can lead to inefficiency, instability and even divergence in the training…

Machine Learning · Computer Science 2019-11-26 Yuguang Yang