English
Related papers

Related papers: Combining Learning from Human Feedback and Knowled…

200 papers

Behavioural cloning uses a dataset of demonstrations to learn a behavioural policy. To overcome various learning and policy adaptation problems, we propose to use latent space to index a demonstration dataset, instantly access similar…

Artificial Intelligence · Computer Science 2023-06-16 Federico Malato , Florian Leopold , Ville Hautamaki , Andrew Melnik

In a search and rescue scenario, rescuers may have different knowledge of the environment and strategies for exploration. Understanding what is inside a rescuer's mind will enable an observer agent to proactively assist them with critical…

Machine Learning · Computer Science 2020-11-23 Vidhi Jain , Rohit Jena , Huao Li , Tejus Gupta , Dana Hughes , Michael Lewis , Katia Sycara

Collaboration is a cornerstone of society. In the real world, human teammates make use of multi-sensory data to tackle challenging tasks in ever-changing environments. It is essential for embodied agents collaborating in visually-rich…

Artificial Intelligence · Computer Science 2024-12-09 Qian Long , Zhi Li , Ran Gong , Ying Nian Wu , Demetri Terzopoulos , Xiaofeng Gao

Humans can leverage hierarchical structures to split a task into sub-tasks and solve problems efficiently. Both imitation and reinforcement learning or a combination of them with hierarchical structures have been proven to be an efficient…

Robotics · Computer Science 2020-12-15 Yaru Niu , Yijun Gu

We study the problem of learning goal-conditioned policies in Minecraft, a popular, widely accessible yet challenging open-ended environment for developing human-level multi-task agents. We first identify two main challenges of learning…

Artificial Intelligence · Computer Science 2023-10-16 Shaofei Cai , Zihao Wang , Xiaojian Ma , Anji Liu , Yitao Liang

Developing interactive agents that can understand language, perceive their surroundings, and act within the physical world is a long-standing goal of AI research. The Minecraft Collaborative Building Task (MCBT) (Narayan-Chen, Jayannavar,…

Assistance games are a promising alternative to reinforcement learning from human feedback (RLHF) for training AI assistants. Assistance games resolve key drawbacks of RLHF, such as incentives for deceptive behavior, by explicitly modeling…

Artificial Intelligence · Computer Science 2025-06-13 Cassidy Laidlaw , Eli Bronstein , Timothy Guo , Dylan Feng , Lukas Berglund , Justin Svegliato , Stuart Russell , Anca Dragan

Contextual dueling bandit is used to model the bandit problems, where a learner's goal is to find the best arm for a given context using observed noisy human preference feedback over the selected arms for the past contexts. However,…

Machine Learning · Computer Science 2025-04-17 Arun Verma , Zhongxiang Dai , Xiaoqiang Lin , Patrick Jaillet , Bryan Kian Hsiang Low

The MineRL competition is designed for the development of reinforcement learning and imitation learning algorithms that can efficiently leverage human demonstrations to drastically reduce the number of environment interactions needed to…

Machine Learning · Computer Science 2021-11-18 Hangyu Mao , Chao Wang , Xiaotian Hao , Yihuan Mao , Yiming Lu , Chengjie Wu , Jianye Hao , Dong Li , Pingzhong Tang

MineObserver 2.0 is an AI framework that uses Computer Vision and Natural Language Processing for assessing the accuracy of learner-generated descriptions of Minecraft images that include some scientifically relevant content. The system…

Artificial Intelligence · Computer Science 2023-12-20 Jay Mahajan , Samuel Hum , Jack Henhapl , Diya Yunus , Matthew Gadbury , Emi Brown , Jeff Ginger , H. Chad Lane

Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such…

Due to the dynamic and unpredictable open-world setting, navigating complex environments in Minecraft poses significant challenges for multi-agent systems. Agents must interact with the environment and coordinate their actions with other…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Zhonghan Zhao , Kewei Chen , Dongxu Guo , Wenhao Chai , Tian Ye , Yanting Zhang , Gaoang Wang

Pre-training Reinforcement Learning agents in a task-agnostic manner has shown promising results. However, previous works still struggle in learning and discovering meaningful skills in high-dimensional state-spaces, such as pixel-spaces.…

Artificial Intelligence · Computer Science 2021-07-20 Juan José Nieto , Roger Creus , Xavier Giro-i-Nieto

Enhancing AI systems with efficient communication skills for effective human assistance necessitates proactive initiatives from the system side to discern specific circumstances and interact aptly. This research focuses on a collective…

Computation and Language · Computer Science 2024-02-09 Jack Zhang

We propose a large scale semantic parsing dataset focused on instruction-driven communication with an agent in Minecraft. We describe the data collection process which yields additional 35K human generated instructions with their semantic…

Computation and Language · Computer Science 2019-05-07 Yacine Jernite , Kavya Srinet , Jonathan Gray , Arthur Szlam

Reactions such as gestures, facial expressions, and vocalizations are an abundant, naturally occurring channel of information that humans provide during interactions. A robot or other agent could leverage an understanding of such implicit…

Human-Computer Interaction · Computer Science 2020-12-08 Yuchen Cui , Qiping Zhang , Alessandro Allievi , Peter Stone , Scott Niekum , W. Bradley Knox

Humans can pursue a near-infinite variety of tasks, but typically can only pursue a small number at the same time. We hypothesize that humans leverage experience on one task to preemptively learn solutions to other tasks that were…

Machine Learning · Computer Science 2026-05-06 Wilka Carvalho , Sam Hall-McMaster , Honglak Lee , Samuel J. Gershman

For machine learning perception problems, human-level classification performance is used as an estimate of top algorithm performance. Thus, it is important to understand as precisely as possible the factors that impact human-level…

Machine Learning · Computer Science 2019-08-27 Josiah I. Clark , Caroline A. Clark

Seamless interaction between AI agents and humans using natural language remains a key goal in AI research. This paper addresses the challenges of developing interactive agents capable of understanding and executing grounded natural…

Artificial Intelligence · Computer Science 2024-07-15 Shrestha Mohanty , Negar Arabzadeh , Andrea Tupini , Yuxuan Sun , Alexey Skrynnik , Artem Zholus , Marc-Alexandre Côté , Julia Kiseleva

In collaborative tasks, effective communication is crucial for achieving joint goals. One such task is collaborative building where builders must communicate with each other to construct desired structures in a simulated environment such as…

Computation and Language · Computer Science 2023-05-11 Zhengxiang Shi , Jerome Ramos , To Eun Kim , Xi Wang , Hossein A. Rahmani , Aldo Lipani