English
Related papers

Related papers: Recursive Reward Aggregation

200 papers

No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error…

Artificial Intelligence · Computer Science 2017-08-22 Tom Everitt , Victoria Krakovna , Laurent Orseau , Marcus Hutter , Shane Legg

Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a…

Machine Learning · Computer Science 2017-11-28 Peter Henderson , Wei-Di Chang , Pierre-Luc Bacon , David Meger , Joelle Pineau , Doina Precup

Scaling up test-time compute, by generating multiple independent solutions and selecting or aggregating among them, has become a central paradigm for improving large language models (LLMs) on challenging reasoning tasks. While most prior…

Computation and Language · Computer Science 2025-09-09 Wenting Zhao , Pranjal Aggarwal , Swarnadeep Saha , Asli Celikyilmaz , Jason Weston , Ilia Kulikov

Building trust in reinforcement learning (RL) agents requires understanding why they make certain decisions, especially in high-stakes applications like robotics, healthcare, and finance. Existing explainability methods often focus on…

Artificial Intelligence · Computer Science 2025-06-18 Rishav Rishav , Somjit Nath , Vincent Michalski , Samira Ebrahimi Kahou

We consider the problem of learning to behave optimally in a Markov Decision Process when a reward function is not specified, but instead we have access to a set of demonstrators of varying performance. We assume the demonstrators are…

Machine Learning · Computer Science 2019-08-01 Pablo Samuel Castro , Shijian Li , Daqing Zhang

We consider reinforcement learning (RL) in Markov Decision Processes in which an agent repeatedly interacts with an environment that is modeled by a controlled Markov process. At each time step $t$, it earns a reward, and also incurs a…

Machine Learning · Computer Science 2023-03-16 Rahul Singh , Abhishek Gupta , Ness B. Shroff

Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a…

Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions. However, state-of-the art methods typically focus on learning a single…

Machine Learning · Computer Science 2022-01-04 Markus Peschl , Arkady Zgonnikov , Frans A. Oliehoek , Luciano C. Siebert

Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and diversity. While reinforcement learning (RL) has been used to…

Machine Learning · Computer Science 2026-03-25 Orhun Buğra Baran , Melih Kandemir , Ramazan Gokberk Cinbis

In classic reinforcement learning (RL) and decision making problems, policies are evaluated with respect to a scalar reward function, and all optimal policies are the same with regards to their expected return. However, many real-world…

Machine Learning · Computer Science 2023-11-02 Han Shao , Lee Cohen , Avrim Blum , Yishay Mansour , Aadirupa Saha , Matthew R. Walter

There are two primary approaches to solving Markov decision problems (MDPs): dynamic programming based on the Bellman equation and linear programming (LP). Dynamic programming methods are the most widely used and form the foundation of both…

Artificial Intelligence · Computer Science 2026-02-24 Donghwan Lee , Hyukjun Yang , Bum Geun Park

We present CRM (Multi-Agent Collaborative Reward Model), a framework that replaces a single black-box reward model with a coordinated team of specialist evaluators to improve robustness and interpretability in RLHF. Conventional reward…

Artificial Intelligence · Computer Science 2026-01-06 Pei Yang , Ke Zhang , Ji Wang , Xiao Chen , Yuxin Tang , Eric Yang , Lynn Ai , Bill Shi

Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values by learning rewards from human preference data. Due to various reasons, however, such data typically takes the form of rankings…

Machine Learning · Computer Science 2024-06-06 Ilgee Hong , Zichong Li , Alexander Bukharin , Yixiao Li , Haoming Jiang , Tianbao Yang , Tuo Zhao

As the capabilities of artificial agents improve, they are being increasingly deployed to service multiple diverse objectives and stakeholders. However, the composition of these objectives is often performed ad hoc, with no clear…

Machine Learning · Computer Science 2023-10-03 Silviu Pitis

Reinforcement fine-tuning with verifiable rewards (RLVR) has emerged as a powerful paradigm for equipping large vision-language models (LVLMs) with agentic capabilities such as tool use and multi-step reasoning. Despite striking empirical…

Machine Learning · Computer Science 2026-04-23 Carter Adams , Rafael Oliveira , Gabriel Almeida , Sofia Torres

The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…

Machine Learning · Computer Science 2024-12-24 Akane Tsuboya , Yu Kono , Tatsuji Takahashi

Reinforcement learning (RL) has shown its strength in challenging sequential decision-making problems. The reward function in RL is crucial to the learning performance, as it serves as a measure of the task completion degree. In real-world…

Machine Learning · Computer Science 2024-02-13 Siyuan Li , Shijie Han , Yingnan Zhao , By Liang , Peng Liu

In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when…

Machine Learning · Computer Science 2025-06-19 Rui Yu , Shenghua Wan , Yucen Wang , Chen-Xiao Gao , Le Gan , Zongzhang Zhang , De-Chuan Zhan

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…

Machine Learning · Computer Science 2025-07-31 Zijing Zhang , Ziyang Chen , Mingxiao Li , Zhaopeng Tu , Xiaolong Li

We study reward-free reinforcement learning (RL) with linear function approximation, where the agent works in two phases: (1) in the exploration phase, the agent interacts with the environment but cannot access the reward; and (2) in the…

Machine Learning · Computer Science 2024-02-15 Junkai Zhang , Weitong Zhang , Quanquan Gu