Reinforcement learning (RL) algorithms provide a sound theoretical basis for building learning control architectures for embedded agents. Unfortunately all of the theory and much ...
Satinder P. Singh, Tommi Jaakkola, Michael I. Jord...
Due to the unavoidable fact that a robot’s sensors will be limited in some manner, it is entirely possible that it can find itself unable to distinguish between differing state...
Learning by imitation has shown to be a powerful paradigm for automated learning in autonomous robots. This paper presents a general framework of learning by imitation for stochas...
This paper presents a technique for mapping partially observable features from multiple uncertain vantage points. The problem of concurrent mapping and localization (CML) is state...
John J. Leonard, Richard J. Rikoski, Paul M. Newma...
This paper examines the problem of finding an optimal policy for a Partially Observable Markov Decision Process (POMDP) when the model is not known or is only poorly specified. W...