Humans are good at solving sequential decision making problems, generalizing from few examples, and transferring this knowledge to solve new unseen problems. These problems remain longstanding open problems for Artificial Intelligence (AI). In the last decade, the planning community has improved the performance of automated planning systems to solve decision making problems by including novel search techniques and heuristics. On the other hand, the learning community has made major breakthroughs in reinforcement learning techniques for solving planning problems. However, industry level scalability and skill/task generalization still remains an open challenge for current AI tools.
This workshop will feature a mix of invited talks, survey talks in a highlights format, as well as presentations of submitted papers. We aim to synthesize and highlight recent research on the topic from multiple sub-fields of AI, including those of reinforcement learning, classical planning, planning under uncertainty, as well as learning for planning. At the end of the workshop we expect to come up with new insights and topics to address the challenges of generalization in planning.
This workshop is the fourth edition of the recurring GenPlan workshop series.
Javier Segovia-Aguas, Institut de Robòtica i Informàtica Industrial, Spain.
Siddharth Srivastava, Arizona State University, USA.
Raquel Fuentetaja, Universidad Carlos III de Madrid, Spain.
Aviv Tamar, Israel Institute for Technology, Israel.
Anders Jonsson, Universitat Pompeu Fabra, Spain.
Workshop related queries can be addressed to a common alias: genplan20\at\gmail.com.