English
Related papers

Related papers: Learning Norms from Stories: A Prior for Value Ali…

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,…

AI agents designed to collaborate with people benefit from models that enable them to anticipate human behavior. However, realistic models tend to require vast amounts of human data, which is often hard to collect. A good prior or…

Machine Learning · Computer Science 2022-11-22 Mesut Yang , Micah Carroll , Anca Dragan

When humans perform a task with an articulated object, they interact with the object only in a handful of ways, while the space of all possible interactions is nearly endless. This is because humans have prior knowledge about what…

Computer Vision and Pattern Recognition · Computer Science 2023-05-30 Liquan Wang , Nikita Dvornik , Rafael Dubeau , Mayank Mittal , Animesh Garg

Machine learning of Theory of Mind (ToM) is essential to build social agents that co-live with humans and other agents. This capacity, once acquired, will help machines infer the mental states of others from observed contextual action…

Machine Learning · Computer Science 2022-04-21 Dung Nguyen , Phuoc Nguyen , Hung Le , Kien Do , Svetha Venkatesh , Truyen Tran

Building a socially intelligent agent involves many challenges. One of which is to track the agent's mental state transition and teach the agent to make decisions guided by its value like a human. Towards this end, we propose to incorporate…

Computation and Language · Computer Science 2022-07-25 Liang Qiu , Yizhou Zhao , Yuan Liang , Pan Lu , Weiyan Shi , Zhou Yu , Song-Chun Zhu

Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of…

Machine Learning · Computer Science 2023-10-31 Joey Hong , Kush Bhatia , Anca Dragan

Vision-and-Language Navigation (VLN) is a natural language grounding task where agents have to interpret natural language instructions in the context of visual scenes in a dynamic environment to achieve prescribed navigation goals.…

Computation and Language · Computer Science 2019-06-03 Haoshuo Huang , Vihan Jain , Harsh Mehta , Jason Baldridge , Eugene Ie

A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains…

As humans interact with autonomous agents to perform increasingly complicated, potentially risky tasks, it is important to be able to efficiently evaluate an agent's performance and correctness. In this paper we formalize and theoretically…

Machine Learning · Computer Science 2021-06-14 Daniel S. Brown , Jordan Schneider , Anca D. Dragan , Scott Niekum

Humans naturally employ linguistic instructions to convey knowledge, a process that proves significantly more complex for machines, especially within the context of multitask robotic manipulation environments. Natural language, moreover,…

Robotics · Computer Science 2024-05-28 Boyuan Zheng , Jianlong Zhou , Fang Chen

Decision-making agents based on pre-trained Large Language Models (LLMs) are increasingly being deployed across various domains of human activity. While their applications are currently rather specialized, several research efforts are…

Machine Learning · Computer Science 2025-05-13 Elizaveta Tennant , Stephen Hailes , Mirco Musolesi

Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override individual alignment. Here…

Physics and Society · Physics 2026-05-12 Giordano De Marzo , Alessandro Bellina , Claudio Castellano , Viola Priesemann , David Garcia

Generating complex behaviors that satisfy the preferences of non-expert users is a crucial requirement for AI agents. Interactive reward learning from trajectory comparisons (a.k.a. RLHF) is one way to allow non-expert users to convey…

Artificial Intelligence · Computer Science 2023-03-01 Lin Guan , Karthik Valmeekam , Subbarao Kambhampati

Understanding human actions is a key problem in computer vision. However, recognizing actions is only the first step of understanding what a person is doing. In this paper, we introduce the problem of predicting why a person has performed…

Computer Vision and Pattern Recognition · Computer Science 2016-12-01 Carl Vondrick , Deniz Oktay , Hamed Pirsiavash , Antonio Torralba

Learning to navigate in a visual environment following natural-language instructions is a challenging task, because the multimodal inputs to the agent are highly variable, and the training data on a new task is often limited. In this paper,…

Computer Vision and Pattern Recognition · Computer Science 2020-04-07 Weituo Hao , Chunyuan Li , Xiujun Li , Lawrence Carin , Jianfeng Gao

Procedural content generation has enabled vast virtual worlds through levels, maps, and quests, but large-scale character generation remains underexplored. We identify two alignment-induced biases in existing methods: a positive moral bias,…

Computation and Language · Computer Science 2026-05-05 Maan Qraitem , Kate Saenko , Bryan A. Plummer

Large language models (LLMs) are increasingly used in social science simulations. While their performance on reasoning and optimization tasks has been extensively evaluated, less attention has been paid to their ability to simulate human…

Computational Engineering, Finance, and Science · Computer Science 2025-08-25 Yuanjun Feng , Vivek Choudhary , Yash Raj Shrestha

Intelligent agents can learn to represent the action spaces of other agents simply by observing them act. Such representations help agents quickly learn to predict the effects of their own actions on the environment and to plan complex…

Machine Learning · Computer Science 2019-02-13 Oleh Rybkin , Karl Pertsch , Konstantinos G. Derpanis , Kostas Daniilidis , Andrew Jaegle

Developing agents that can quickly adapt their behavior to new tasks remains a challenge. Meta-learning has been applied to this problem, but previous methods require either specifying a reward function which can be tedious or providing…

Artificial Intelligence · Computer Science 2019-07-03 Mark Woodward , Chelsea Finn , Karol Hausman

Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that…

Machine Learning · Computer Science 2023-07-14 Glen Berseth , Florian Golemo , Christopher Pal