10.9k citations
- SLAC National Accelerator LaboratoryUS1.1k papers
- Kavli Institute for Particle Astrophysics and CosmologyUS902 papers
- Centre National de la Recherche ScientifiqueFR526 papers
- University of California, BerkeleyUS493 papers
- California Institute of TechnologyUS458 papers
- Lawrence Berkeley National LaboratoryUS422 papers
- University of MichiganUS401 papers
- University of ChicagoUS390 papers
- Massachusetts Institute of TechnologyUS370 papers
- University College LondonGB333 papers
- University of Maryland, College ParkUS325 papers
- University of California, Santa CruzUS321 papers
5 papers · 2 filters
Hierarchical Planning for Resource Allocation in Emergency Response Systems
Geoffrey Pettet, Ayan Mukhopadhyay, Mykel Kochenderfer +1
A classical problem in city-scale cyber-physical systems (CPS) is resource allocation under uncertainty. Typically, such problems are modeled as Markov (or semi-Markov) decision pr…
Image Generation With Neural Cellular Automatas
Mingxiang Chen, Zhecheng Wang
In this paper, we propose a novel approach to generate images (or other artworks) by using neural cellular automatas (NCAs). Rather than training NCAs based on single images one by…
Structured Policy Iteration for Linear Quadratic Regulator
Youngsuk Park, Ryan A. Rossi, Zheng Wen +2
Linear quadratic regulator (LQR) is one of the most popular frameworks to tackle continuous Markov decision process tasks. With its fundamental theory and tractable optimal policy,…
Experience Replay with Likelihood-free Importance Weights
Samarth Sinha, Jiaming Song, Animesh Garg +1
The use of past experiences to accelerate temporal difference (TD) learning of value functions, or experience replay, is a key component in deep reinforcement learning. Prioritizat…
Point-Based Methods for Model Checking in Partially Observable Markov Decision Processes
Maxime Bouton, Jana Tumova, Mykel J. Kochenderfer
Autonomous systems are often required to operate in partially observable environments. They must reliably execute a specified objective even with incomplete information about the s…