— In the lion and man game, a lion tries to capture a man who is as fast as the lion. We study a new version of this game which takes place in a Euclidean environment with a circ...
Improving the sample efficiency of reinforcement learning algorithms to scale up to larger and more realistic domains is a current research challenge in machine learning. Model-ba...
: Users of front office applications such as call center or customer support applications make millions and millions of decisions each day without analytical support. For example, ...
: Development of capital intensive systems, such as offshore oil platforms or other industrial infrastructure, generally requires a significant amount of capital investment under v...
Jijun Lin, Olivier de Weck, Richard de Neufville, ...
Abstract— We propose a new approximate algorithm, LAJIV (Lookahead J-MDP Information Value), to solve Oracular Partially Observable Markov Decision Problems (OPOMDPs), a special ...