Professor András LörinczThe Robot World News article Ms. Pac-Man Plays Herself said
In the latest feat of artificial intelligence (AI), researchers have taught AI agents to play Ms. Pac-Man and sometimes do it better than humans. The study, performed by Istvan Szita and Andras Lorincz from the Department of Information Systems at Eotvos University in Hungary, showed that AI agents can successfully be taught how to strategize through reinforcement learning. The researchers hope that teaching Ms. Pac-Man will be an ideal means to explore what artificial intelligence is still missing.
The researchers explain that games are ideal test environments for reinforcement learning (RL). Since the late 1950s, RL has been tested in classical games, such as checkers, backgammon, and chess. Since the 2000s, researchers have begun testing RL on modern computer games, such as the role-playing game Baldur’s Gate, the strategy game Wargus, and Tetris.
András Lörincz, Ph.D., CSc, FECCAI
is Head Senior Researcher, Neural Information Processing Group,
Eötvös Loránd University, Budapest,
His research focuses on distributed intelligent systems and their applications in neurobiological and cognitive modeling, as well as medicine. He founded the Neural Information Processing Group of Eötvös University and he directs a multidisciplinary team of mathematicians, programmers, computer scientists and physicists. He has acted as the PI of several successful international projects in collaboration with Panasonic, Honda Future Technology Research, and the Information Directorate of the US Air Force in the fields of hardware-software co-synthesis, image processing, and human-computer collaboration.
András graduated in physics at the Eötvös Loránd University in 1975 where he earned his PhD in 1978 and his CSc in 1986 in experimental and theoretical solid-state physics and chemical physics, respectively. He conducted research and taught quantum control, photoacoustics, and artificial intelligence at the Hungarian Academy of Sciences, University of Chicago, Brown University, Princeton University, the Illinois Institute of Technology, and ETH Zurich. He authored about 200 peer reviewed scientific publications. In 1997–1998 he was the scientific director of the Hungarian subsidiary of US-based Associative Computing Ltd.
He has received the Széchenyi Professor Award, Master Professor Award and the Széchenyi István Award in 2000, 2001, and 2004, respectively. Four of his students won the prestigious Pro Scientia Gold Medal in the field of information science over the last 4 years. In 2004, he was awarded the Kalmár Prize of the John von Neumann Computer Society of Hungary. He became an elected Fellow of the European Coordinating Committee for Artificial Intelligence in 2006.
András coauthored Auto-Regressive Independent Process Analysis without Combinatorial Efforts, Learning to Play Using Low-Complexity Rule-Based Policies: Illustrations through Ms. Pac-Man, Undercomplete Blind Subspace Deconvolution via Linear Prediction, Independent Process Analysis without A Priori Dimensional Information, Co-learning and the development of communication, Post Nonlinear Independent Subspace Analysis, Peer-to-peer networks: A language theoretic approach, Mind model seems necessary for the emergence of communication, and Independent Subspace Analysis can Cope with the “Curse of Dimensionality”. Read the full list of his publications!