English
Related papers

Related papers: No Metrics Are Perfect: Adversarial Reward Learnin…

200 papers

Research on Inverse Reinforcement Learning (IRL) from third-person videos has shown encouraging results on removing the need for manual reward design for robotic tasks. However, most prior works are still limited by training from a…

Machine Learning · Computer Science 2022-08-02 Sateesh Kumar , Jonathan Zamora , Nicklas Hansen , Rishabh Jangir , Xiaolong Wang

Verification and validation of autonomous driving (AD) systems and components is of increasing importance, as such technology increases in real-world prevalence. Safety-critical scenario generation is a key approach to robustify AD policies…

Robotics · Computer Science 2025-07-15 Benjamin Stoler , Ingrid Navarro , Jonathan Francis , Jean Oh

Deep neural networks coupled with fast simulation and improved computation have led to recent successes in the field of reinforcement learning (RL). However, most current RL-based approaches fail to generalize since: (a) the gap between…

Machine Learning · Computer Science 2017-03-09 Lerrel Pinto , James Davidson , Rahul Sukthankar , Abhinav Gupta

We study how to generate captions that are not only accurate in describing an image but also discriminative across different images. The problem is both fundamental and interesting, as most machine-generated captions, despite phenomenal…

Computer Vision and Pattern Recognition · Computer Science 2019-03-12 Dianqi Li , Qiuyuan Huang , Xiaodong He , Lei Zhang , Ming-Ting Sun

Imitation learning in a high-dimensional environment is challenging. Most inverse reinforcement learning (IRL) methods fail to outperform the demonstrator in such a high-dimensional environment, e.g., Atari domain. To address this…

Machine Learning · Computer Science 2020-09-14 Xingrui Yu , Yueming Lyu , Ivor W. Tsang

Training a high-dimensional simulated agent with an under-specified reward function often leads the agent to learn physically infeasible strategies that are ineffective when deployed in the real world. To mitigate these unnatural behaviors,…

Artificial Intelligence · Computer Science 2022-03-30 Alejandro Escontrela , Xue Bin Peng , Wenhao Yu , Tingnan Zhang , Atil Iscen , Ken Goldberg , Pieter Abbeel

In this paper, we propose a novel conditional-generative-adversarial-nets-based image captioning framework as an extension of traditional reinforcement-learning (RL)-based encoder-decoder architecture. To deal with the inconsistent…

Computer Vision and Pattern Recognition · Computer Science 2020-09-10 Chen Chen , Shuai Mu , Wanpeng Xiao , Zexiong Ye , Liesi Wu , Qi Ju

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Computation and Language · Computer Science 2024-02-20 Meng Cao , Lei Shu , Lei Yu , Yun Zhu , Nevan Wichers , Yinxiao Liu , Lei Meng

Auxiliary Learning (AL) is a form of multi-task learning in which a model trains on auxiliary tasks to boost performance on a primary objective. While AL has improved generalization across domains such as navigation, image classification,…

Machine Learning · Computer Science 2025-11-05 Judah Goldfeder , Matthew So , Hod Lipson

Reward function specification, which requires considerable human effort and iteration, remains a major impediment for learning behaviors through deep reinforcement learning. In contrast, providing visual demonstrations of desired behaviors…

Machine Learning · Computer Science 2022-06-29 Rafael Rafailov , Tianhe Yu , Aravind Rajeswaran , Chelsea Finn

Inverse reinforcement learning (IRL), which infers reward functions from demonstrations, is a valuable tool for modeling and understanding decision-making behavior. Many variants of IRL have been developed to capture complexities of human…

Machine Learning · Computer Science 2026-05-14 Leo Benac , Abhishek Sharma , Alihan Huyuk , Finale Doshi-Velez

Single-model systems often suffer from deficiencies in tasks such as speaker verification (SV) and image classification, relying heavily on partial prior knowledge during decision-making, resulting in suboptimal performance. Although…

Machine Learning · Computer Science 2024-04-25 Zuheng Kang , Yayun He , Jianzong Wang , Junqing Peng , Jing Xiao

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL.To solve this problem, many strategies…

Computation and Language · Computer Science 2021-04-13 Zhengxu Hou , Bang Liu , Ruihui Zhao , Zijing Ou , Yafei Liu , Xi Chen , Yefeng Zheng

Large language models (LLMs) possess strong multilingual capabilities, and combining Reinforcement Learning from Human Feedback (RLHF) with translation tasks has shown great potential. However, we observe that this paradigm performs…

Computation and Language · Computer Science 2025-08-06 Tianjiao Li , Mengran Yu , Chenyu Shi , Yanjun Zhao , Xiaojing Liu , Qiang Zhang , Qi Zhang , Xuanjing Huang , Jiayin Wang

In offline reinforcement learning (RL) agents are trained using a logged dataset. It appears to be the most natural route to attack real-life applications because in domains such as healthcare and robotics interactions with the environment…

Machine Learning · Computer Science 2020-12-15 Ksenia Konyushkova , Konrad Zolna , Yusuf Aytar , Alexander Novikov , Scott Reed , Serkan Cabi , Nando de Freitas

Inverse Reinforcement Learning (IRL) is the problem of finding a reward function which describes observed/known expert behavior. The IRL setting is remarkably useful for automated control, in situations where the reward function is…

Machine Learning · Computer Science 2022-09-12 Gregory Dexter , Kevin Bello , Jean Honorio

Rewards serve as a measure of user satisfaction and act as a limiting factor in interactive recommender systems. In this research, we focus on the problem of learning to reward (LTR), which is fundamental to reinforcement learning. Previous…

Machine Learning · Computer Science 2023-10-31 Jialin Liu , Xinyan Su , Zeyu He , Xiangyu Zhao , Jun Li

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

Recent text-only models demonstrate remarkable mathematical reasoning capabilities. Extending these to visual domains requires vision-language models to translate images into text descriptions. However, current models, trained to produce…

Machine Learning · Computer Science 2025-10-01 John Gkountouras , Ivan Titov

This paper presents a novel approach for unsupervised video summarization using reinforcement learning (RL), addressing limitations like unstable adversarial training and reliance on heuristic-based reward functions. The method operates on…

Multimedia · Computer Science 2025-12-24 Mehryar Abbasi , Hadi Hadizadeh , Parvaneh Saeedi
‹ Prev 1 4 5 6 7 8 10 Next ›