Cognitive Systems and Robotics One of the aspirations of machine learning is to develop intelligent systems that can address a wide variety of control problems of many different types. Currently, the technology used to specify, solve and analyse one control problem typically cannot be reused on a different problem. The purpose of CompLACS is to develop a unified toolkit that will incorporate the most successful approaches to control problems within a single framework, including bandit problems, Markov Decision Processes (MDPs), Partially Observable MDPs (POMDPs), continuous stochastic control, and multi-agent systems. The toolkit will also provide a generic interface to specifying problems and analysing performance, by mapping intuitive, human-understandable goals into machine-understandable objectives, and by mapping algorithm performance and get back into human-understandable terms.
Field of science
- /natural sciences/computer and information sciences/artificial intelligence/machine learning
Call for proposal
See other projects for this call
Funding SchemeCP - Collaborative project (generic)