Reinforcement Learning and Planning for Large-Scale Systems

Invited talks

  • 30 June 2016: PI Lucian Busoniu is invited to City University London to present the project work on planning.
  • 19 April 2016: PI Lucian Busoniu is invited to the Delft Center for Systems and Control to give a talk on Planning for near-optimal nonlinear control with continuous actions.
  • 2 Oct 2015: PI Lucian Busoniu is invited to give a talk on the basics of reinforcement learning and planning, at the IROS 2015 workshop on Machine Learning in Planning and Control of Robot Motion.
  • 24-25 Sept 2014: PI Lucian Busoniu is invited to the Advanced Robotics department of the Italian Institute of Technology, to talk on planning and applications.
  • 26 June 2014: Lucian Busoniu presents Optimistic Planning: Algorithms and Control Applications at a brainstorming meeting at LAMIH, University of Valenciennes.
  • 9 Dec 2013: PI Lucian Busoniu gives a talk on planning and reinforcement learning at the workshop Intelligent Planning and Control: Bringing Together Adaptive Control and Reinforcement Learning for Guaranteeing Optimal Performance and Robustness, organized at the 52nd IEEE Conference on Decision and Control, Florence, Italy.
  • 19 Sept 2013: Team member Koppany Mathe presents his work on Optimistic Planning for Nonlinear Systems with Long Ranges of Constant Controls at the Research Center for Automatic Control of Nancy, France.

Additional dissemination and impact

  • A second offshoot cooperation project called NETASSIST has been funded by IFA and AUF (budget 33KEUR; partners TUCluj, the University of Szeged, and CRAN Nancy).
  • The book Handling Uncertainty and Networked Structure in Robot Control edited by team members Lucian Busoniu and Levente Tamas is now in the final stages of production with Springer, see also the publications page.
  • Lucian Busoniu is coorganizing the 2015 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, the engineering event that is closest in topic to the project.
  • With important equipment contributions from the project (robot arm, tracking camera system, other sensors and actuators), the team starts a lab on robotics within the Automation Department of the Technical University of Cluj Napoca. An associated research group on Robotics and Nonlinear Control (ROCON) is created.
  • Lucian Busoniu has also been coorganizing the 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning.
  • PHC Brancusi international cooperation project between UTCluj and the Research Center for Automatic Control of Nancy is accepted for funding. Project title: Artificial-Intelligence-Based Optimization for the Stable and Optimal Control of Networked Systems (AICONS). Romanian PI: Lucian Busoniu, French PI: Constantin Morarescu.