English
Related papers

Related papers: Bellman Error Centering

200 papers

In reinforcement learning, two objective functions have been developed extensively in the literature: discounted and averaged rewards. The generalization to an entropy-regularized setting has led to improved robustness and exploration for…

Machine Learning · Computer Science 2025-01-20 Jacob Adamczyk , Volodymyr Makarenko , Stas Tiomkin , Rahul V. Kulkarni

In reinforcement learning (RL), aligning agent behavior with specific objectives typically requires careful design of the reward function, which can be challenging when the desired objectives are complex. In this work, we propose an…

Machine Learning · Computer Science 2025-09-05 Yuting Tang , Yivan Zhang , Johannes Ackermann , Yu-Jie Zhang , Soichiro Nishimori , Masashi Sugiyama

We study value-iteration (VI) algorithms for solving general (a.k.a. multichain) Markov decision processes (MDPs) under the average-reward criterion, a fundamental but theoretically challenging setting. Beyond the difficulties inherent to…

Optimization and Control · Mathematics 2026-04-23 Matthew Zurek , Yudong Chen

Value function approximation is important in modern reinforcement learning (RL) problems especially when the state space is (infinitely) large. Despite the importance and wide applicability of value function approximation, its theoretical…

Machine Learning · Computer Science 2023-02-24 Hanlin Zhu , Ruosong Wang , Jason D. Lee

Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show…

Machine Learning · Computer Science 2026-05-08 Jeongjae Lee , Jinho Chang , Jeongsol Kim , Jong Chul Ye

Off-policy temporal-difference (TD) learning with function approximation faces a structural tradeoff among stability, projection geometry, and variance control. Emphatic TD (ETD) improves the off-policy projection geometry through follow-on…

Artificial Intelligence · Computer Science 2026-05-07 Xingguo Chen , Chaohui Wu , Jinguo Ye , Chao Li , Shangdong Yang , Guang Yang , Tianyu Liang , Wenhao Wang

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

Reinforcement learning algorithms in multi-agent systems deliver highly resilient and adaptable solutions for common problems in telecommunications,aerospace, and industrial robotics. However, achieving an optimal global goal remains a…

Multiagent Systems · Computer Science 2021-05-18 Changgang Zheng , Shufan Yang , Juan Parra-Ullauri , Antonio Garcia-Dominguez , Nelly Bencomo

Conventional off-policy reinforcement learning (RL) focuses on maximizing the expected return of scalar rewards. Distributional RL (DRL), in contrast, studies the distribution of returns with the distributional Bellman operator in a…

Machine Learning · Statistics 2024-08-15 Dong Neuck Lee , Michael R. Kosorok

We study the problem of estimating Dynamic Discrete Choice (DDC) models, also known as offline Maximum Entropy-Regularized Inverse Reinforcement Learning (offline MaxEnt-IRL) in machine learning. The objective is to recover reward or $Q^*$…

Machine Learning · Computer Science 2026-05-06 Enoch H. Kang , Hema Yoganarasimhan , Lalit Jain

Value function learning plays a central role in many state-of-the-art reinforcement-learning algorithms. Many popular algorithms like Q-learning do not optimize any objective function, but are fixed-point iterations of some variant of…

Machine Learning · Computer Science 2020-01-10 Yihao Feng , Lihong Li , Qiang Liu

Conditional value-at-risk (CVaR) is a prominent risk measure in financial engineering, energy systems, and supply chain management. In these domains, Markov decision processes (MDPs) with a long-run CVaR criterion effectively mitigate cost…

Optimization and Control · Mathematics 2026-03-11 Qixin Wang , Hao Cao , Jian-Qiang Hu , Mingjie Hu , Li Xia

This paper develops an online inverse reinforcement learning algorithm aimed at efficiently recovering a reward function from ongoing observations of an agent's actions. To reduce the computation time and storage space in reward estimation,…

Robotics · Computer Science 2017-08-01 Kun Li , Joel W. Burdick

Gradient-based methods for value estimation in reinforcement learning have favorable stability properties, but they are typically much slower than Temporal Difference (TD) learning methods. We study the root causes of this slowness and show…

Machine Learning · Computer Science 2023-07-25 Arsalan Sharifnassab , Richard Sutton

Reward allocation, also known as the credit assignment problem, has been an important topic in economics, engineering, and machine learning. An important concept in reward allocation is the core, which is the set of stable allocations where…

Computer Science and Game Theory · Computer Science 2024-11-01 Nam Phuong Tran , The Anh Ta , Shuqing Shi , Debmalya Mandal , Yali Du , Long Tran-Thanh

Reinforcement learning from verifiable rewards (RLVR) has emerged as a central technique for improving the reasoning capabilities of large language models. Despite its effectiveness, how response-level rewards translate into token-level…

Machine Learning · Computer Science 2026-05-21 Kaiyi Zhang , Wei Wu , Yankai Lin

We present the first finite-sample analysis of policy evaluation in robust average-reward Markov Decision Processes (MDPs). Prior work in this setting have established only asymptotic convergence guarantees, leaving open the question of…

Machine Learning · Statistics 2025-12-11 Yang Xu , Washim Uddin Mondal , Vaneet Aggarwal

Reinforcement learning (RL) algorithms typically deal with maximizing the expected cumulative return (discounted or undiscounted, finite or infinite horizon). However, several crucial applications in the real world, such as drug discovery,…

A growing trend for value-based reinforcement learning (RL) algorithms is to capture more information than scalar value functions in the value network. One of the most well-known methods in this branch is distributional RL, which models…

Machine Learning · Computer Science 2021-10-27 Pushi Zhang , Xiaoyu Chen , Li Zhao , Wei Xiong , Tao Qin , Tie-Yan Liu

Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward learning, where reward functions are inferred from human feedback rather than manually specified.…

Machine Learning · Computer Science 2026-01-16 Chaitanya Kharyal , Calarina Muslimani , Matthew E. Taylor