Noisy sensing, imperfect control, and environment changes are defining characteristics of many real-world robot tasks. The partially observable Markov decision process (POMDP) …
D Silver, J Veness - Advances in neural information …, 2010 - proceedings.neurips.cc
This paper introduces a Monte-Carlo algorithm for online planning in large POMDPs. The algorithm combines a Monte-Carlo update of the agent's belief state with a Monte-Carlo tree …
G Shani, J Pineau, R Kaplow - Autonomous Agents and Multi-Agent …, 2013 - Springer
The past decade has seen a significant breakthrough in research on solving partially observable Markov decision processes (POMDPs). Where past solvers could not scale …
From household appliances to applications in robotics, engineered systems involving complex dynamics can only be as effective as the algorithms that control them. While …
D Golovin, A Krause - Journal of Artificial Intelligence Research, 2011 - jair.org
Many problems in artificial intelligence require adaptively making a sequence of decisions with uncertain outcomes under partial observability. Solving such stochastic optimization …
The development of autonomous vehicles for urban driving has seen rapid progress in the past 30 years. This paper provides a summary of the current state of the art in autonomous …
S Ross, J Pineau, S Paquet, B Chaib-Draa - Journal of Artificial Intelligence …, 2008 - jair.org
Abstract Partially Observable Markov Decision Processes (POMDPs) provide a rich framework for sequential decision-making under uncertainty in stochastic domains …
In this work, we consider the regret minimization problem for reinforcement learning in latent Markov Decision Processes (LMDP). In an LMDP, an MDP is randomly drawn from a set of …
R Munos - Foundations and Trends® in Machine Learning, 2014 - nowpublishers.com
This work covers several aspects of the optimism in the face of uncertainty principle applied to large scale optimization problems under finite numerical budget. The initial motivation for …