Approximate and Compensate: A method for risk-sensitive meta-deliberation and continual computation

We present a flexible procedure for a resource-bounded agent to allocate limited computational resources to on-line problem solving. Our APPROXIMATE AND COMPENSATE methodology extends a well-known greedy time-slicing approach to conditions in which performance profiles may be non-concave and there is uncertainty in the environment and/or problem-solving procedures of an agent. With this method, the agent first approximates problem-solving performance and problem parameters with standard parameterized models. Second, the agent computes a risk-management factor that compensates for the risk inherent in the approximation. The risk-management factor represents a mean-variance tradeoff that may be derived optimally off-line using any available information. Theoretical and experimental results demonstrate that APPROXIMATE AND COMPENSATE extends existing methods to new problems and expands the practical application of meta-deliberation.

[1]  Bart Selman,et al.  Algorithm portfolios , 2001, Artif. Intell..

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

[3]  Amy L. Lansky,et al.  Reactive Reasoning and Planning , 1987, AAAI.

[4]  Shlomo Zilberstein,et al.  Operational Rationality through Compilation of Anytime Algorithms , 1995, AI Mag..

[5]  Shlomo Zilberstein,et al.  Anytime Sensing Planning and Action: A Practical Model for Robot Control , 1993, IJCAI.

[6]  Oren Etzioni,et al.  Embedding Decision-Analytic Control in a Learning Architecture , 1991, Artif. Intell..

[7]  Shlomo Zilberstein,et al.  Using Anytime Algorithms in Intelligent Systems , 1996, AI Mag..

[8]  John S. Breese,et al.  Ideal Partition of Resources for Metareasoning , 2021, ArXiv.

[9]  Eric Horvitz,et al.  Perception, Attention, and Resources: A Decision-Theoretic Approach to Graphics Rendering , 1997, UAI.

[10]  Eric Horvitz,et al.  Principles and applications of continual computation , 2001, Artif. Intell..

[11]  Shlomo Zilberstein,et al.  Optimal Composition of Real-Time Systems , 1996, Artif. Intell..

[12]  A. Rosenfeld,et al.  IEEE TRANSACTIONS ON SYSTEMS , MAN , AND CYBERNETICS , 2022 .

[13]  David C. Parkes,et al.  On the Optimality of Greedy Meta-Deliberation , 2003 .

[14]  Lloyd G. Greenwald,et al.  Time to laparotomy for intra-abdominal bleeding from trauma does affect survival for delays up to 90 minutes. , 2002, The Journal of trauma.

[15]  Eric Horvitz,et al.  Computational tradeoffs under bounded resources , 2001, Artif. Intell..

[16]  Victor R. Lesser,et al.  Design-to-time real-time scheduling , 1993, IEEE Trans. Syst. Man Cybern..

[17]  Eric Horvitz,et al.  Bounded Conditioning: Flexible Inference for Decisions under Scarce Resources , 2013, UAI 1989.

[18]  Michael P. Wellman,et al.  Planning and Control , 1991 .

[19]  Thomas Dean,et al.  Solving Time-critical Decision-making Problems with Predictable Computational Demands , 1994, AIPS.