Search Results for author:
Found 11 papers, 3 papers with code
Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models
However, to solve inference tasks that were not seen during training, these models (EGMs) often need to be re-trained.
Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video
Such models, however, are approximate, which limits their applicability.
A Sufficient Statistic for Influence in Structured Multiagent Environments
In these ways, this paper deepens our understanding of abstraction in a wide range of sequential decision making settings, providing the basis for new approaches and algorithms for a large class of problems.
Combining Physical Simulators and Object-Based Networks for Control
Physics engines play an important role in robot planning and control; however, many real-world control problems involve complex contact dynamics that cannot be characterized analytically.
Modular meta-learning in abstract graph networks for combinatorial generalization
Modular meta-learning is a new framework that generalizes to unseen datasets by combining a small set of neural modules in different ways.
Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing
An efficient, generalizable physical simulator with universal uncertainty estimates has wide applications in robot state estimation, planning, and control.
Modular meta-learning
Many prediction problems, such as those that arise in the context of robotics, have a simplifying underlying structure that, if known, could accelerate learning.
Finding Frequent Entities in Continuous Data
In many applications that involve processing high-dimensional data, it is important to identify a small set of entities that account for a significant fraction of detections.
Learning to Acquire Information
Finding the optimal subset of observations is intractable in general, thus we focus on the problem of active diagnosis, where the agent selects the next most-informative observation based on the results of previous observations.
Planning for Decentralized Control of Multiple Robots Under Uncertainty
We describe a probabilistic framework for synthesizing control policies for general multi-robot systems, given environment and sensor models and a cost function.
Multi-Agent Filtering with Infinitely Nested Beliefs
In partially observable worlds with many agents, nested beliefs are formed when agents simultaneously reason about the unknown state of the world and the beliefs of the other agents.
