English
Related papers

Related papers: AssistanceZero: Scalably Solving Assistance Games

200 papers

Bilevel optimization has been recently applied to many machine learning tasks. However, their applications have been restricted to the supervised learning setting, where static objective functions with benign structures are considered. But…

Machine Learning · Computer Science 2024-06-04 Han Shen , Zhuoran Yang , Tianyi Chen

As artificial intelligence becomes increasingly intelligent---in some cases, achieving superhuman performance---there is growing potential for humans to learn from and collaborate with algorithms. However, the ways in which AI systems…

Artificial Intelligence · Computer Science 2020-07-15 Reid McIlroy-Young , Siddhartha Sen , Jon Kleinberg , Ashton Anderson

Existing approaches to language model alignment often treat safety as a tradeoff against helpfulness, which can lead to unacceptable responses in sensitive domains. To ensure reliable performance in such settings, we propose High-Confidence…

Machine Learning · Computer Science 2025-06-11 Yaswanth Chittepu , Blossom Metevier , Will Schwarzer , Austin Hoag , Scott Niekum , Philip S. Thomas

Open-world survival games pose significant challenges for AI algorithms due to their multi-tasking, deep exploration, and goal prioritization requirements. Despite reinforcement learning (RL) being popular for solving games, its high sample…

Artificial Intelligence · Computer Science 2023-12-13 Yue Wu , Shrimai Prabhumoye , So Yeon Min , Yonatan Bisk , Ruslan Salakhutdinov , Amos Azaria , Tom Mitchell , Yuanzhi Li

We consider the problem of creating assistants that can help agents solve new sequential decision problems, assuming the agent is not able to specify the reward function explicitly to the assistant. Instead of acting in place of the agent…

Machine Learning · Computer Science 2022-12-01 Sebastiaan De Peuter , Samuel Kaski

This paper introduces MazeBase: an environment for simple 2D games, designed as a sandbox for machine learning approaches to reasoning and planning. Within it, we create 10 simple games embodying a range of algorithmic tasks (e.g. if-then…

Machine Learning · Computer Science 2016-01-08 Sainbayar Sukhbaatar , Arthur Szlam , Gabriel Synnaeve , Soumith Chintala , Rob Fergus

Re-inforcement learning from human feedback (RLHF) has been effective in the task of AI alignment. However, one of the key assumptions of RLHF is that the annotators (referred to as workers from here on out) have a homogeneous response…

Human-Computer Interaction · Computer Science 2026-01-29 Sarvesh Shashidhar , Abhishek Mishra , Madhav Kotecha

In this paper we propose a formal, model-agnostic meta-learning framework for safe reinforcement learning. Our framework is inspired by how parents safeguard their children across a progression of increasingly riskier tasks, imparting a…

Machine Learning · Computer Science 2024-11-01 Nabil Omi , Hosein Hasanbeig , Hiteshi Sharma , Sriram K. Rajamani , Siddhartha Sen

With the rapid advancement of AI, software engineering increasingly relies on AI-driven approaches, particularly language models (LMs), to enhance code performance. However, the trustworthiness and reliability of LMs remain significant…

Software Engineering · Computer Science 2025-03-19 Jingzhi Gong

Recently, the seminal algorithms AlphaGo and AlphaZero have started a new era in game learning and deep reinforcement learning. While the achievements of AlphaGo and AlphaZero - playing Go and other complex games at super human level - are…

Machine Learning · Computer Science 2022-09-27 Johannes Scheiermann , Wolfgang Konen

Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human…

Computation and Language · Computer Science 2023-10-10 Yi Dong , Zhilin Wang , Makesh Narsimhan Sreedhar , Xianchao Wu , Oleksii Kuchaiev

Training deep reinforcement learning agents complex behaviors in 3D virtual environments requires significant computational resources. This is especially true in environments with high degrees of aliasing, where many states share nearly…

Machine Learning · Computer Science 2019-08-06 Spencer Frazier , Mark Riedl

Although reinforcement learning (RL) has emerged as a promising approach for improving vision-language models (VLMs) and multimodal large language models (MLLMs), current methods rely heavily on manually curated datasets and costly human…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Qinsi Wang , Bo Liu , Tianyi Zhou , Jing Shi , Yueqian Lin , Yiran Chen , Hai Helen Li , Kun Wan , Wentian Zhao

Reinforcement learning has enabled agents to solve challenging tasks in unknown environments. However, manually crafting reward functions can be time consuming, expensive, and error prone to human error. Competing objectives have been…

Machine Learning · Computer Science 2021-02-11 Brendon Matusch , Jimmy Ba , Danijar Hafner

Reinforcement learning (RL) is an area of research that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games. This success is primarily due to the vast…

Artificial Intelligence · Computer Science 2018-08-16 Per-Arne Andersen , Morten Goodwin , Ole-Christoffer Granmo

While Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning generative AI, we present empirical evidence that it can also cause severe, systematic misalignment. We hypothesize that this stems from evaluator…

Machine Learning · Computer Science 2025-06-11 Kaiqu Liang , Haimin Hu , Ryan Liu , Thomas L. Griffiths , Jaime Fernández Fisac

Rigorously evaluating machine intelligence against the broad spectrum of human general intelligence has become increasingly important and challenging in this era of rapid technological advance. Conventional AI benchmarks typically assess…

Many reinforcement learning environments (e.g., Minecraft) provide only sparse rewards that indicate task completion or failure with binary values. The challenge in exploration efficiency in such environments makes it difficult for…

Artificial Intelligence · Computer Science 2024-04-02 Hao Li , Xue Yang , Zhaokai Wang , Xizhou Zhu , Jie Zhou , Yu Qiao , Xiaogang Wang , Hongsheng Li , Lewei Lu , Jifeng Dai

Reinforcement learning from human feedback (RLHF) has contributed to performance improvements in large language models. To tackle its reliance on substantial amounts of human-labeled data, a successful approach is multi-task representation…

Machine Learning · Computer Science 2025-03-06 Ruitao Chen , Liwei Wang

In mixed-initiative systems, the mode of AI assistance delivery can be as consequential as the assistance itself. We investigated two assistance delivery modes: on-demand help (users request via Button) and pre-scheduled help (assistance…

Human-Computer Interaction · Computer Science 2026-02-03 Yunhao Luo , Arthur Caetano , Avinash Ajit Nargund , Tobias Höllerer , Misha Sra