English
Related papers

Related papers: Intuitive Physics Guided Exploration for Sample Ef…

200 papers

Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel problems. This principle spans a range of approaches,…

Machine Learning · Computer Science 2025-10-14 Sarthak Mittal , Divyat Mahajan , Guillaume Lajoie , Mohammad Pezeshki

Modeling group actions on latent representations enables controllable transformations of high-dimensional image data. Prior works applying group-theoretic priors or modeling transformations typically operate in the high-dimensional data…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Farhana Hossain Swarnali , Miaomiao Zhang , Tonmoy Hossain

In this work, we propose a method for learning driver models that account for variables that cannot be observed directly. When trained on a synthetic dataset, our models are able to learn encodings for vehicle trajectories that distinguish…

Machine Learning · Computer Science 2017-04-20 Jeremy Morton , Mykel J. Kochenderfer

While intelligent tutoring systems (ITSs) can use information from past students to personalize instruction, each new student is unique. Moreover, the education problem is inherently difficult because the learning process is only partially…

Machine Learning · Computer Science 2025-11-20 Jeffrey Jiang , Kevin Hong , Emily Kuczynski , Gregory Pottie

Reinforcement learning agents often exhibit unintended goal-directed behaviour outside their training distribution, but we currently lack a principled understanding of how such agents will generalise to novel environments based on their…

Machine Learning · Computer Science 2026-05-25 Jason Ross Brown , Edward James Young

Consider a prosthetic arm, learning to adapt to its user's control signals. We propose Interaction-Grounded Learning for this novel setting, in which a learner's goal is to interact with the environment with no grounding or explicit reward…

Machine Learning · Computer Science 2021-07-15 Tengyang Xie , John Langford , Paul Mineiro , Ida Momennejad

Grounding the common-sense reasoning of Large Language Models (LLMs) in physical domains remains a pivotal yet unsolved problem for embodied AI. Whereas prior works have focused on leveraging LLMs directly for planning in symbolic spaces,…

Robotics · Computer Science 2024-12-10 Yanwei Wang , Tsun-Hsuan Wang , Jiayuan Mao , Michael Hagenow , Julie Shah

In recent years, reinforcement learning (RL) has shown remarkable success in robotics when a fast and accurate simulator is available for a given task. When using RL and simulation, more simulator realism is generally beneficial but becomes…

Robotics · Computer Science 2026-04-17 Yunfu Deng , Yuhao Li , Josiah P. Hanna

Autonomous reinforcement learning agents, like children, do not have access to predefined goals and reward functions. They must discover potential goals, learn their own reward functions and engage in their own learning trajectory.…

Machine Learning · Computer Science 2019-11-11 Nicolas Lair , Cédric Colas , Rémy Portelas , Jean-Michel Dussoux , Peter Ford Dominey , Pierre-Yves Oudeyer

Mutual Information between agent Actions and environment States (MIAS) quantifies the influence of agent on its environment. Recently, it was found that the maximization of MIAS can be used as an intrinsic motivation for artificial agents.…

Machine Learning · Computer Science 2020-08-04 Ruihan Zhao , Stas Tiomkin , Pieter Abbeel

Machine learning techniques are powerful tools for construction of emulators for complex systems. We explore different machine learning methods and conceptual methodologies, ranging from functional approximations to dynamical…

Dynamical Systems · Mathematics 2021-01-01 Hannah Lu , Dinara Ermakova , Haruko Murakami Wainwright , Liange Zheng , Daniel M. Tartakovsky

Recent advancements in video generation have enabled the development of ``world models'' capable of simulating potential futures for robotics and planning. However, specifying precise goals for these models remains a challenge; text…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Nate Gillman , Yinghua Zhou , Zitian Tang , Evan Luo , Arjan Chakravarthy , Daksh Aggarwal , Michael Freeman , Charles Herrmann , Chen Sun

Simulation parameter settings such as contact models and object geometry approximations are critical to training robust robotic policies capable of transferring from simulation to real-world deployment. Previous approaches typically…

Robotics · Computer Science 2023-10-03 Allen Z. Ren , Hongkai Dai , Benjamin Burchfiel , Anirudha Majumdar

The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward…

Machine Learning · Computer Science 2019-11-05 Nicholas C. Landolfi , Garrett Thomas , Tengyu Ma

Video representation learning has recently attracted attention in computer vision due to its applications for activity and scene forecasting or vision-based planning and control. Video prediction models often learn a latent representation…

Computer Vision and Pattern Recognition · Computer Science 2020-09-18 Rama Krishna Kandukuri , Jan Achterhold , Michael Möller , Jörg Stückler

Projective Simulation was introduced as a novel approach to Artificial Intelligence. It involves a deliberation procedure that consists of a random walk on a graph of clips and allows for the learning agent to project itself into the future…

Quantum Physics · Physics 2017-08-02 Amara Katabarwa , Nima Karimatari

As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the…

Machine Learning · Computer Science 2025-04-25 Ruichu Cai , Siyang Huang , Jie Qiao , Wei Chen , Yan Zeng , Keli Zhang , Fuchun Sun , Yang Yu , Zhifeng Hao

Recent advances in data-driven models for grounded language understanding have enabled robots to interpret increasingly complex instructions. Two fundamental limitations of these methods are that most require a full model of the environment…

Robotics · Computer Science 2019-10-23 Siddharth Patki , Ethan Fahnestock , Thomas M. Howard , Matthew R. Walter

Learning models of the environment from pure interaction is often considered an essential component of building lifelong reinforcement learning agents. However, the common practice in model-based reinforcement learning is to learn models…

Machine Learning · Computer Science 2023-06-13 Safa Alver , Doina Precup

In order to mitigate the sample complexity of real-world reinforcement learning, common practice is to first train a policy in a simulator where samples are cheap, and then deploy this policy in the real world, with the hope that it…

Machine Learning · Computer Science 2024-10-29 Andrew Wagenmaker , Kevin Huang , Liyiming Ke , Byron Boots , Kevin Jamieson , Abhishek Gupta