Anytime Bounded Rationality

Dependable cyber-physical systems strive to deliver anticipative, multi-objective performance anytime, facing deluges of inputs with varying and limited resources. This is even more challenging for life-long learning rational agents as they also have to contend with the varying and growing know-how accumulated from experience. These issues are of crucial practical value, yet have been only marginally and unsatisfactorily addressed in AGI research. We present a value-driven computational model of anytime bounded rationality robust to variations of both resources and knowledge. It leverages continually learned knowledge to anticipate, revise and maintain concurrent courses of action spanning over arbitrary time scales for execution anytime necessary.

[1]  Pei Wang.  Rigid Flexibility: The Logic of Intelligence (Applied Logic Series) , 2006 .

[2]  John R Anderson,et al.  An integrated theory of the mind. , 2004, Psychological review.

[3]  Joel Veness,et al.  A Monte-Carlo AIXI Approximation , 2009, J. Artif. Intell. Res..

[4]  Stuart C. Shapiro,et al.  Anchoring in a grounded layered architecture with integrated reasoning , 2003, Robotics Auton. Syst..

[5]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[6]  Mark S. Boddy,et al.  Deliberation Scheduling for Problem Solving in Time-Constrained Environments , 1994, Artif. Intell..

[7]  John E. Laird,et al.  The Soar Cognitive Architecture , 2012 .

[8]  Jürgen Schmidhuber,et al.  Bounded Seed-AGI , 2014, AGI.

[9]  B. Baars,et al.  The Timing of the Cognitive Cycle , 2011, PloS one.

[10]  Andrés Faiña,et al.  Multilevel Darwinist Brain (MDB): Artificial Evolution in a Cognitive Architecture for Real Robots , 2010, IEEE Transactions on Autonomous Mental Development.

[11]  Pat Langley,et al.  Interleaving Learning , Problem Solving , and Execution in the Icarus Architecture , 2022 .

[12]  Magdalena D. Bugajska,et al.  An Architecture for Adaptive Algorithmic Hybrids , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[13]  Pei Wang,et al.  Rigid Flexibility: The Logic of Intelligence , 2006 .

[14]  Eric Horvitz,et al.  Time-Dependent Utility and Action Under Uncertainty , 1991, UAI.

[15]  Jürgen Schmidhuber,et al.  AUTONOMOUS ACQUISITION OF NATURAL LANGUAGE , 2014, ICIS 2014.