English
Related papers

Related papers: FORM: Learning Expressive and Transferable First-O…

200 papers

Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper,…

This paper presents PROB-IRM, an approach that learns robust reward machines (RMs) for reinforcement learning (RL) agents from noisy execution traces. The key aspect of RM-driven RL is the exploitation of a finite-state machine that…

Artificial Intelligence · Computer Science 2025-03-24 Roko Parac , Lorenzo Nodari , Leo Ardon , Daniel Furelos-Blanco , Federico Cerutti , Alessandra Russo

Standard reward models typically predict scalar scores that fail to capture the multifaceted nature of response quality in non-verifiable domains, such as creative writing or open-ended instruction following. To address this limitation, we…

Computation and Language · Computer Science 2026-02-13 Ran Xu , Tianci Liu , Zihan Dong , Tony Yu , Ilgee Hong , Carl Yang , Linjun Zhang , Tao Zhao , Haoyu Wang

We present LARL-RM (Large language model-generated Automaton for Reinforcement Learning with Reward Machine) algorithm in order to encode high-level knowledge into reinforcement learning using automaton to expedite the reinforcement…

Machine Learning · Computer Science 2024-02-13 Shayan Meshkat Alsadat , Jean-Raphael Gaglione , Daniel Neider , Ufuk Topcu , Zhe Xu

Reinforcement learning (RL) relies heavily on exploration to learn from its environment and maximize observed rewards. Therefore, it is essential to design a reward function that guarantees optimal learning from the received experience.…

Artificial Intelligence · Computer Science 2022-06-20 Ingy ElSayed-Aly , Lu Feng

It has previously been shown that by using reinforcement learning (RL), agents can derive simple approximate and exact-restricted numeral systems that are similar to human ones (Carlsson, 2021). However, it is a major challenge to show how…

Computation and Language · Computer Science 2025-05-20 Andrea Silvi , Jonathan Thomas , Emil Carlsson , Devdatt Dubhashi , Moa Johansson

Most algorithms in reinforcement learning (RL) require that the objective is formalised with a Markovian reward function. However, it is well-known that certain tasks cannot be expressed by means of an objective in the Markov rewards…

Machine Learning · Computer Science 2024-02-20 Rohan Subramani , Marcus Williams , Max Heitmann , Halfdan Holm , Charlie Griffin , Joar Skalse

Dense process rewards have proven a more effective alternative to the sparse outcome-level rewards in the inference-time scaling of large language models (LLMs), particularly in tasks requiring complex multi-step reasoning. While dense…

We propose a reinforcement learning based approach to query object localization, for which an agent is trained to localize objects of interest specified by a small exemplary set. We learn a transferable reward signal formulated using the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-16 Tingfeng Li , Shaobo Han , Martin Renqiang Min , Dimitris N. Metaxas

Reward modeling (RM), which captures human preferences to align large language models (LLMs), is increasingly employed in tasks such as model finetuning, response filtering, and ranking. However, due to the inherent complexity of human…

Computation and Language · Computer Science 2026-04-09 Pankayaraj Pathmanathan , Furong Huang

Generative reward models (GRMs) for vision-language models (VLMs) often evaluate outputs via a three-stage pipeline: rubric generation, criterion-based scoring, and a final verdict. However, the intermediate rubric is rarely optimized…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Weijie Qiu , Dai Guan , Junxin Wang , Zhihang Li , Yongbo Gai , Mengyu Zhou , Erchao Zhao , Xiaoxi Jiang , Guanjun Jiang

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 show that memory-augmented Transformers can implement the entire class of linear first-order methods (LFOMs), a class that contains gradient descent (GD) and more advanced methods such as conjugate gradient descent (CGD), momentum…

Machine Learning · Computer Science 2025-02-04 Sanchayan Dutta , Suvrit Sra

Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…

Artificial Intelligence · Computer Science 2025-03-19 Anukriti Singh , Amisha Bhaskar , Peihong Yu , Souradip Chakraborty , Ruthwik Dasyam , Amrit Bedi , Pratap Tokekar

Both animals and artificial agents benefit from state representations that support rapid transfer of learning across tasks and which enable them to efficiently traverse their environments to reach rewarding states. The successor…

Machine Learning · Computer Science 2021-11-09 Ted Moskovitz , Spencer R. Wilson , Maneesh Sahani

Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process reward modeling offers an alternative but incurs high computational costs, reward hacking…

Artificial Intelligence · Computer Science 2026-05-29 Xiao Feng , Bo Han , Zhanke Zhou , Jiaqi Fan , Jiangchao Yao , Ka Ho Li , Dahai Yu , Michael Kwok-Po Ng

Many real-world applications require an agent to make robust and deliberate decisions with multimodal information (e.g., robots with multi-sensory inputs). However, it is very challenging to train the agent via reinforcement learning (RL)…

Machine Learning · Computer Science 2023-02-21 Jinming Ma , Feng Wu , Yingfeng Chen , Xianpeng Ji , Yu Ding

Despite the fact that deep reinforcement learning (RL) has surpassed human-level performances in various tasks, it still has several fundamental challenges. First, most RL methods require intensive data from the exploration of the…

Machine Learning · Computer Science 2021-07-06 Zhe Xu , Bo Wu , Aditya Ojha , Daniel Neider , Ufuk Topcu

In this work, we propose a novel framework for the logical specification of non-Markovian rewards in Markov Decision Processes (MDPs) with large state spaces. Our approach leverages Linear Temporal Logic Modulo Theories over finite traces…

Artificial Intelligence · Computer Science 2026-02-09 Pierriccardo Olivieri , Fausto Lasca , Alessandro Gianola , Matteo Papini

Reward engineering has long been a challenge in Reinforcement Learning (RL) research, as it often requires extensive human effort and iterative processes of trial-and-error to design effective reward functions. In this paper, we propose…

Robotics · Computer Science 2024-06-18 Yufei Wang , Zhanyi Sun , Jesse Zhang , Zhou Xian , Erdem Biyik , David Held , Zackory Erickson