The Thirty-Sixth AAAI Conference on Artificial Intelligence was held virtually from February 22-March 1, 2022. The conference program cochairs were Vasant Honavar (Pennsylvania State University, USA) and Matthijs Spaan (Delft University of Technology, Netherlands). The AAAI-22 program consisted of a diverse technical track, student abstracts, poster sessions, invited speakers, tutorials, workshops, and exhibit and competition programs. Additionally, the program included a special track on AI for Social Impact, recognizing that high-quality research on social impact domains often leads to papers that differ from traditional AAAI submissions along multiple dimensions. The conference was colocated with the Thirty-Fourth Innovative Applications of Artificial Intelligence Conference (cochaired by Mark Boddy, Adventium Labs, USA, and Meinolf Sellmann, Shopify, USA). The IAAI conference traditionally consists of case studies of deployed applications with measurable benefits whose value depends on the use of AI technology, as well as emerging applications, which discuss efforts to apply AI tools, techniques, or methods to real world problems. The IAAI papers are included in these proceedings. Also included are the papers from the Twelfth AAAI Symposium on Educational Advances in Artificial Intelligence (cochaired by Michael Guerzhoy, University of Toronto, Canada, and Marion Neumann, Washington University in St. Louis, USA). The EAAI conference invites a broad range of papers on teaching AI and teaching with AI framed as research papers or as experience reports.

Sequential decision making under uncertainty has gained significant traction in Artificial Intelligence. In many applications, dealing explicitly with uncertainty regarding the effects of actions, state of the environment and possibly the behavior of other agents is crucial to achieve satisfactory task performance. Decision-theoretic planning models like the Markov decision process (MDP), the partially observable MDP (POMDP) and their many multiagent extensions have emerged as the dominant paradigm for this purpose. This symposium provided a dedicated forum for researchers of computational sequential decision making under uncertainty to meet and share ideas.