Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Andrey Kolobov

Heuristic-Guided Reinforcement Learning

Jun 05, 2021
Ching-An Cheng, Andrey Kolobov, Adith Swaminathan

  Access Paper or Ask Questions

Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL

Jun 04, 2021
Bogdan Mazoure, Ahmed M. Ahmed, Patrick MacAlpine, R Devon Hjelm, Andrey Kolobov

  Access Paper or Ask Questions

Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark

Mar 29, 2021
Sharada Mohanty, Jyotish Poonganam, Adrien Gaidon, Andrey Kolobov, Blake Wulfe, Dipam Chakraborty, Gražvydas Šemetulskis, João Schapke, Jonas Kubilius, Jurgis Pašukonis, Linas Klimas, Matthew Hausknecht, Patrick MacAlpine, Quang Nhat Tran, Thomas Tumiel, Xiaocheng Tang, Xinwei Chen, Christopher Hesse, Jacob Hilton, William Hebgen Guss, Sahika Genc, John Schulman, Karl Cobbe

  Access Paper or Ask Questions

Policy Improvement from Multiple Experts

Jul 01, 2020
Ching-An Cheng, Andrey Kolobov, Alekh Agarwal

  Access Paper or Ask Questions

Safe Reinforcement Learning via Curriculum Induction

Jun 22, 2020
Matteo Turchetta, Andrey Kolobov, Shital Shah, Andreas Krause, Alekh Agarwal

  Access Paper or Ask Questions

Online Learning for Active Cache Synchronization

Feb 27, 2020
Andrey Kolobov, Sébastien Bubeck, Julian Zimmert

  Access Paper or Ask Questions

ArduSoar: an Open-Source Thermalling Controller for Resource-Constrained Autopilots

Aug 21, 2018
Samuel Tabor, Iain Guilliard, Andrey Kolobov

  Access Paper or Ask Questions

Autonomous Thermalling as a Partially Observable Markov Decision Process (Extended Version)

May 24, 2018
Iain Guilliard, Richard Rogahn, Jim Piavis, Andrey Kolobov

  Access Paper or Ask Questions

Metareasoning for Planning Under Uncertainty

May 03, 2015
Christopher H. Lin, Andrey Kolobov, Ece Kamar, Eric Horvitz

* Extended version of IJCAI 2015 paper 

  Access Paper or Ask Questions

A Theory of Goal-Oriented MDPs with Dead Ends

Oct 16, 2012
Andrey Kolobov, Mausam, Daniel Weld

* Appears in Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI2012) 

  Access Paper or Ask Questions