English
Related papers

Related papers: Music Generation using Human-In-The-Loop Reinforce…

200 papers

Humans are able to understand and perform complex tasks by strategically structuring the tasks into incremental steps or subgoals. For a robot attempting to learn to perform a sequential task with critical subgoal states, such states can…

Human-Computer Interaction · Computer Science 2018-06-25 Xinlei Pan , Eshed Ohn-Bar , Nicholas Rhinehart , Yan Xu , Yilin Shen , Kris M. Kitani

Inverse Reinforcement Learning (IRL) and Reinforcement Learning from Human Feedback (RLHF) are pivotal methodologies in reward learning, which involve inferring and shaping the underlying reward function of sequential decision-making…

Machine Learning · Computer Science 2024-10-16 Kihyun Kim , Jiawei Zhang , Asuman Ozdaglar , Pablo A. Parrilo

We approach the problem of learning by watching humans in the wild. While traditional approaches in Imitation and Reinforcement Learning are promising for learning in the real world, they are either sample inefficient or are constrained to…

Robotics · Computer Science 2022-07-20 Shikhar Bahl , Abhinav Gupta , Deepak Pathak

Due to the limited smartness and abilities of machine intelligence, currently autonomous vehicles are still unable to handle all kinds of situations and completely replace drivers. Because humans exhibit strong robustness and adaptability…

Robotics · Computer Science 2021-04-16 Jingda Wu , Zhiyu Huang , Chao Huang , Zhongxu Hu , Peng Hang , Yang Xing , Chen Lv

Development of machine learning (ML) workflows is a tedious process of iterative experimentation: developers repeatedly make changes to workflows until the desired accuracy is attained. We describe our vision for a "human-in-the-loop" ML…

Databases · Computer Science 2018-04-18 Doris Xin , Litian Ma , Jialin Liu , Stephen Macke , Shuchen Song , Aditya Parameswaran

Human explanation (e.g., in terms of feature importance) has been recently used to extend the communication channel between human and agent in interactive machine learning. Under this setting, human trainers provide not only the ground…

Artificial Intelligence · Computer Science 2021-10-28 Lin Guan , Mudit Verma , Sihang Guo , Ruohan Zhang , Subbarao Kambhampati

In human-robot interaction (HRI) systems, such as autonomous vehicles, understanding and representing human behavior are important. Human behavior is naturally rich and diverse. Cost/reward learning, as an efficient way to learn and…

Robotics · Computer Science 2020-08-24 Liting Sun , Zheng Wu , Hengbo Ma , Masayoshi Tomizuka

Open-domain dialog generation is a challenging problem; maximum likelihood training can lead to repetitive outputs, models have difficulty tracking long-term conversational goals, and training on standard movie or online datasets may lead…

Machine Learning · Computer Science 2020-01-03 Abdelrhman Saleh , Natasha Jaques , Asma Ghandeharioun , Judy Hanwen Shen , Rosalind Picard

Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of…

Machine Learning · Computer Science 2025-12-30 Timo Kaufmann , Paul Weng , Viktor Bengs , Eyke Hüllermeier

Designing an effective reward function has long been a challenge in reinforcement learning, particularly for complex tasks in unstructured environments. To address this, various learning paradigms have emerged that leverage different forms…

Machine Learning · Computer Science 2025-04-29 Muhammad Qasim Elahi , Somtochukwu Oguchienti , Maheed H. Ahmed , Mahsa Ghasemi

This study proposes a system designed to enumerate the process of collaborative composition among humans, using automatic music composition technology. By integrating multiple Recurrent Neural Network (RNN) models, the system provides an…

Sound · Computer Science 2024-03-07 So Hirawata , Noriko Otani

Reinforcement Learning (RL) has shown promise for aligning Large Language Models (LLMs) to follow instructions with various constraints. Despite the encouraging results, RL improvement inevitably relies on sampling successful, high-quality…

Artificial Intelligence · Computer Science 2025-12-30 Kongcheng Zhang , Qi Yao , Shunyu Liu , Wenjian Zhang , Min Cen , Yang Zhou , Wenkai Fang , Yiru Zhao , Baisheng Lai , Mingli Song

Building Reinforcement Learning (RL) algorithms which are able to adapt to continuously evolving tasks is an open research challenge. One technology that is known to inherently handle such non-stationary input patterns well is Hierarchical…

Machine Learning · Computer Science 2020-09-21 Jakob Struye , Kevin Mets , Steven Latré

Reinforcement learning from human feedback (RLHF) has emerged as a central framework for aligning large language models (LLMs) with human preferences. Despite its practical success, RLHF raises fundamental statistical questions because it…

Machine Learning · Statistics 2026-04-06 Pangpang Liu , Chengchun Shi , Will Wei Sun

We study human-in-the-loop reinforcement learning (RL) with trajectory preferences, where instead of receiving a numeric reward at each step, the agent only receives preferences over trajectory pairs from a human overseer. The goal of the…

Machine Learning · Computer Science 2022-05-25 Xiaoyu Chen , Han Zhong , Zhuoran Yang , Zhaoran Wang , Liwei Wang

Information systems increasingly leverage artificial intelligence (AI) and machine learning (ML) to generate value from vast amounts of data. However, ML models are imperfect and can generate incorrect classifications. Hence,…

Machine Learning · Computer Science 2023-07-10 Johannes Jakubik , Daniel Weber , Patrick Hemmer , Michael Vössing , Gerhard Satzger

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising…

Machine Learning · Computer Science 2022-11-30 Jingda Wu , Zhiyu Huang , Wenhui Huang , Chen Lv

We introduce MusicLM, a model generating high-fidelity music from text descriptions such as "a calming violin melody backed by a distorted guitar riff". MusicLM casts the process of conditional music generation as a hierarchical…

Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e.g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences.…

Computation and Language · Computer Science 2023-08-07 Chenglong Wang , Hang Zhou , Yimin Hu , Yifu Huo , Bei Li , Tongran Liu , Tong Xiao , Jingbo Zhu

In real-time and safety-critical cyber-physical systems (CPSs), control synthesis must guarantee that generated policies meet stringent timing and correctness requirements under uncertain and dynamic conditions. Signal temporal logic (STL)…

Artificial Intelligence · Computer Science 2025-10-10 Xiaochen Tang , Zhenya Zhang , Miaomiao Zhang , Jie An