This paper presents an activity recognition approach based on the tracking of a specific human actor’s current object manipulation actions, complemented by two kinds of situation...
Dipak Surie, Thomas Pederson, Fabien Lagriffoul, L...
Learning agents, whether natural or artificial, must update their internal parameters in order to improve their behavior over time. In reinforcement learning, this plasticity is ...
Dealing with numerical information is practically important in many real-world planning domains where the executability of an action can depend on certain numerical conditions, an...
Abstract— This paper deals with the long run average continuous control problem of piecewise deterministic Markov processes (PDMP‘s) taking values in a general Borel space and ...
This paper promotes accountability as a central design goal for dependable networked systems. We define three properties for accountable systems that extend beyond the basic secu...