Causal Learning Workshop at NeurIPS
We propose to combine reinforcement learning and theoretical physics to describe effective theories of agency. This involves understanding the connection between the physics notion of causality and how intelligent agents can arise as a useful effective description within some environments. We discuss cases where such an effective theory of agency can break down and suggest a broader framework incorporating theory of mind for expanding the notion of agency in the presence of other agents that can predict actions. We comment on implications for superintelligence and whether physical bounds can be used to place limits on such predictors.
Donglai Xiang, Timur Bagautdinov, Tuur Stuyck, Fabian Prada, Javier Romero, Weipeng Xu, Shunsuke Saito, Jingfan Guo, Breannan Smith, Takaaki Shiratori, Yaser Sheikh, Jessica Hodgins, Chenglei Wu
Ludwig Sidenmark, Mark Parent, Chi-Hao Wu, Joannes Chan, Michael Glueck, Daniel Wigdor, Tovi Grossman, Marcello Giordano
Xingyi Zhou, Rohit Girdhar, Armand Joulin, Philipp Krähenbühl, Ishan Misra
