Logical foundations of artificial intelligence
Logical foundations of artificial intelligence
Do the right thing: studies in limited rationality
Do the right thing: studies in limited rationality
Tractable decision-analytic control
Proceedings of the first international conference on Principles of knowledge representation and reasoning
Proceedings of the first international conference on Principles of knowledge representation and reasoning
Planning and control
Toward efficient agnostic learning
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Optimal speedup of Las Vegas algorithms
Information Processing Letters
Operational rationality through compilation of anytime algorithms
Operational rationality through compilation of anytime algorithms
On complexity as bounded rationality (extended abstract)
STOC '94 Proceedings of the twenty-sixth annual ACM symposium on Theory of computing
Control of problem solving: principles and architecture
UAI '88 Proceedings of the Fourth Annual Conference on Uncertainty in Artificial Intelligence
A Markovian extension of Valiant's learning model
SFCS '90 Proceedings of the 31st Annual Symposium on Foundations of Computer Science
Intention reconsideration in complex environments
AGENTS '00 Proceedings of the fourth international conference on Autonomous agents
The computational complexity of boolean and stochastic agent design problems
Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 2
A Roadmap of Agent Research and Development
Autonomous Agents and Multi-Agent Systems
Intelligent Agents: The Key Concepts
Proceedings of the 9th ECCAI-ACAI/EASSS 2001, AEMAS 2001, HoloMAS 2001 on Multi-Agent-Systems and Applications II-Selected Revised Papers
On Augmenting Reactivity with Deliberation in a Controlled Manner
Balancing Reactivity and Social Deliberation in Multi-Agent Systems, From RoboCup to Real-World Applications (selected papers from the ECAI 2000 Workshop and additional contributions)
Logic, Knowledge Representation, and Bayesian Decision Theory
CL '00 Proceedings of the First International Conference on Computational Logic
The Belief-Desire-Intention Model of Agency
ATAL '98 Proceedings of the 5th International Workshop on Intelligent Agents V, Agent Theories, Architectures, and Languages
Intention Reconsideration Reconsidered
ATAL '98 Proceedings of the 5th International Workshop on Intelligent Agents V, Agent Theories, Architectures, and Languages
The Computational Complexity of Agent Verification
ATAL '01 Revised Papers from the 8th International Workshop on Intelligent Agents VIII
Layered and Resource-Adapting Agents in the RoboCup Simulation
RoboCup-98: Robot Soccer World Cup II
Optimistic and Disjunctive Agent Design Problems
ATAL '00 Proceedings of the 7th International Workshop on Intelligent Agents VII. Agent Theories Architectures and Languages
Near rationality and competitive equilibria in networked systems
Proceedings of the ACM SIGCOMM workshop on Practice and theory of incentives in networked systems
The complexity of agent design problems: Determinism and history dependence
Annals of Mathematics and Artificial Intelligence
Metacognition in computation: a selected research review
Artificial Intelligence
Avoiding logical omniscience and perfect reasoning: a survey
AI Communications
Applied Artificial Intelligence
Learning when to stop thinking and do something!
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Using performance profile trees to improve deliberation control
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Towards flexible multi-agent decision-making under time pressure
IJCAI'99 Proceedings of the 16th international joint conference on Artifical intelligence - Volume 1
Definition and complexity of some basic metareasoning problems
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Approximating optimal policies for agents with limited execution resources
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Field review: Metacognition in computation: A selected research review
Artificial Intelligence
Problem-solving methods: understanding, description, development, and reuse
Problem-solving methods: understanding, description, development, and reuse
Informing decisions: how people use online rating information to make choices
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Negotiation in electronic commerce: a study in the Latin-American market
KES'11 Proceedings of the 15th international conference on Knowledge-based and intelligent information and engineering systems - Volume Part II
On the formulation of competitive negotiations in Web applications: The Latin-American market case
Expert Systems with Applications: An International Journal
Virtual games: a new approach to implementation of social choice rules
CEEMAS'05 Proceedings of the 4th international Central and Eastern European conference on Multi-Agent Systems and Applications
Using inertia and referrals to facilitate satisficing distributions
IWDC'05 Proceedings of the 7th international conference on Distributed Computing
A theory of goal-oriented communication
Journal of the ACM (JACM)
Space-Time embedded intelligence
AGI'12 Proceedings of the 5th international conference on Artificial General Intelligence
Hi-index | 0.00 |
Since its inception, artificial intelligence has relied upon a theoretical foundation centred around perfect rationality as the desired property of intelligent systems. We argue, as others have done, that this foundation is inadequate because it imposes fundamentally unsatisfiable requirements. As a result, there has arisen a wide gap between theory and practice in AI, hindering progress in the field. We propose instead a property called bounded optimality. Roughly speaking, an agent is bounded-optimal if its program is a solution to the constrained optimization problem presented by its architecture and the task environment. We show how to construct agents with this property for a simple class of machine architectures in a broad class of real-time environments. We illustrate these results using a simple model of an automated mail sorting facility. We also define a weaker property, asymptotic bounded optimality (ABO), that generalizes the notion of optimality in classical complexity theory. We then construct universal ABO programs, i.e., programs that are ABO no matter what real-time constraints are applied. Universal ABO programs can be used as building blocks for more complex systems. We conclude with a discussion of the prospects for bounded optimality as a theoretical basis for AI, and relate it to similar trends in philosophy, economics, and game theory.