English
Related papers

Related papers: Marginal Utility for Planning in Continuous or Lar…

200 papers

Active learning aims to reduce annotation cost by predicting which samples are useful for a human expert to label. Although this field is quite old, several important challenges to using active learning in real-world settings still remain…

Machine Learning · Computer Science 2021-04-27 Louis Desreumaux , Vincent Lemaire

Agents that can autonomously navigate the web through a graphical user interface (GUI) using a unified action space (e.g., mouse and keyboard actions) can require very large amounts of domain-specific expert demonstrations to achieve good…

Artificial Intelligence · Computer Science 2025-04-25 Lynn Cherif , Flemming Kondrup , David Venuto , Ankit Anand , Doina Precup , Khimya Khetarpal

In recent years, learning-based approaches have revolutionized motion planning. The data generation process for these methods involves caching a large number of high quality paths for different queries (start, goal pairs) in various…

Robotics · Computer Science 2023-03-14 Sagar Suhas Joshi , Panagiotis Tsiotras

Direct optimization is an appealing framework that replaces integration with optimization of a random objective for approximating gradients in models with discrete random variables. A$^\star$ sampling is a framework for optimizing such…

Machine Learning · Computer Science 2020-10-26 Guy Lorberbom , Chris J. Maddison , Nicolas Heess , Tamir Hazan , Daniel Tarlow

Model-based curiosity combines active learning approaches to optimal sampling with the information gain based incentives for exploration presented in the curiosity literature. Existing model-based curiosity methods look to approximate…

Robotics · Computer Science 2020-11-12 Bernadette Bucher , Karl Schmeckpeper , Nikolai Matni , Kostas Daniilidis

Despite recent advances, goal-directed generation of structured discrete data remains challenging. For problems such as program synthesis (generating source code) and materials design (generating molecules), finding examples which satisfy…

Machine Learning · Computer Science 2020-10-26 Amina Mollaysa , Brooks Paige , Alexandros Kalousis

We introduce a framework for model learning and planning in stochastic domains with continuous state and action spaces and non-Gaussian transition models. It is efficient because (1) local models are estimated only when the planner requires…

Artificial Intelligence · Computer Science 2018-08-06 Zi Wang , Stefanie Jegelka , Leslie Pack Kaelbling , Tomás Lozano-Pérez

Mental simulation is a critical cognitive function for goal-directed behavior because it is essential for assessing actions and their consequences. When a self-generated or externally specified goal is given, a sequence of actions that is…

Robotics · Computer Science 2019-03-13 Minju Jung , Takazumi Matsumoto , Jun Tani

A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behavior to unseen goals, such policies may also enable…

Machine Learning · Computer Science 2019-02-21 Paulo Rauber , Avinash Ummadisingu , Filipe Mutz , Juergen Schmidhuber

Sample-efficient online reinforcement learning often uses replay buffers to store experience for reuse when updating the value function. However, uniform replay is inefficient, since certain classes of transitions can be more relevant to…

Machine Learning · Computer Science 2025-05-12 Renhao Wang , Kevin Frans , Pieter Abbeel , Sergey Levine , Alexei A. Efros

This article makes discrete masked models for the generative modeling of discrete data controllable. The goal is to generate samples of a discrete random variable that adheres to a posterior distribution, satisfies specific constraints, or…

Machine Learning · Computer Science 2024-10-04 Wei Guo , Yuchen Zhu , Molei Tao , Yongxin Chen

Leveraging machine learning methods to solve constraint satisfaction problems has shown promising, but they are mostly limited to a static situation where the problem description is completely known and fixed from the beginning. In this…

Machine Learning · Computer Science 2025-09-23 Wook Lee , Frans A. Oliehoek

The objective of this work is to augment the basic abilities of a robot by learning to use new sensorimotor primitives to enable the solution of complex long-horizon problems. Solving long-horizon problems in complex domains requires…

Robotics · Computer Science 2018-08-14 Zi Wang , Caelan Reed Garrett , Leslie Pack Kaelbling , Tomás Lozano-Pérez

It is widely believed that given the same labeling budget, active learning (AL) algorithms like margin-based active learning achieve better predictive performance than passive learning (PL), albeit at a higher computational cost. Recent…

Machine Learning · Computer Science 2023-06-05 Alexandru Tifrea , Jacob Clarysse , Fanny Yang

Online, sample-based planning algorithms for POMDPs have shown great promise in scaling to problems with large state spaces, but they become intractable for large action and observation spaces. This is particularly problematic in multiagent…

Artificial Intelligence · Computer Science 2014-12-23 Christopher Amato , Frans A. Oliehoek

Randomized sampling based algorithms are widely used in robot motion planning due to the problem's intractability, and are experimentally effective on a wide range of problem instances. Most variants do not sample uniformly at random, and…

Active inference has emerged as an alternative approach to control problems given its intuitive (probabilistic) formalism. However, despite its theoretical utility, computational implementations have largely been restricted to…

Machine Learning · Computer Science 2022-03-01 Aswin Paul , Noor Sajid , Manoj Gopalkrishnan , Adeel Razi

This paper considers a problem where multiple users make repeated decisions based on their own observed events. The events and decisions at each time step determine the values of a utility function and a collection of penalty functions. The…

Optimization and Control · Mathematics 2013-05-13 Michael J. Neely

We introduce marginalization models (MAMs), a new family of generative models for high-dimensional discrete data. They offer scalable and flexible generative modeling by explicitly modeling all induced marginal distributions.…

Machine Learning · Computer Science 2024-10-08 Sulin Liu , Peter J. Ramadge , Ryan P. Adams

We study a multi-objective model on the allocation of reusable resources under model uncertainty. Heterogeneous customers arrive sequentially according to a latent stochastic process, request for certain amounts of resources, and occupy…

Optimization and Control · Mathematics 2023-08-02 Xilin Zhang , Wang Chi Cheung