Principles of artificial intelligence
Principles of artificial intelligence
Design and validation of computer protocols
Design and validation of computer protocols
Completing the temporal picture
Selected papers of the 16th international colloquium on Automata, languages, and programming
Planning and control
An approach to anytime learning
ML92 Proceedings of the ninth international workshop on Machine learning
Learning Probabilistic Automata and Markov Chains via Queries
Machine Learning
Memory-efficient algorithms for the verification of temporal properties
Formal Methods in System Design - Special issue on computer-aided verification: general methods
Emergent coordination through the use of cooperative state-changing rules
AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
Theoretical Computer Science
Computer-aided verification of coordinating processes: the automata-theoretic approach
Computer-aided verification of coordinating processes: the automata-theoretic approach
Least-cost flaw repair: a plan refinement strategy for partial-order planning
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
The first law of robotics (a call to arms)
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
On social laws for artificial agent societies: off-line design
Artificial Intelligence - Special volume on computational research on interaction and agency, part 2
Formal methods: state of the art and future directions
ACM Computing Surveys (CSUR) - Special ACM 50th-anniversary issue: strategic directions in computing research
The design and analysis of a computational model of cooperative coevolution
The design and analysis of a computational model of cooperative coevolution
Using Abstraction and Model Checking to Detect Safety Violations in Requirements Specifications
IEEE Transactions on Software Engineering
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Introduction Theory of Automata and Sequential Machines
Introduction Theory of Automata and Sequential Machines
Well-Behaved Borgs, Bolos, and Berserkers
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Modelling techniques for evolving distributed applications
Proceedings of the 7th IFIP WG6.1 International Conference on Formal Description Techniques VII
Incremental Model Checking in the Modal Mu-Calculus
CAV '94 Proceedings of the 6th International Conference on Computer Aided Verification
On Explicit Plan Languages for Coordinating Multiagent Plan Execution
ATAL '97 Proceedings of the 4th International Workshop on Intelligent Agents IV, Agent Theories, Architectures, and Languages
Using Artificial Physics to Control Agents
ICIIS '99 Proceedings of the 1999 International Conference on Information Intelligence and Systems
Distributed Spatial Control, Global Monitoring and Steering of Mobile Agents
ICIIS '99 Proceedings of the 1999 International Conference on Information Intelligence and Systems
Version spaces: an approach to concept learning.
Version spaces: an approach to concept learning.
Learning models of intelligent agents
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
Machine learning and inductive logic programming for multi-agent systems
Mutli-agents systems and applications
An Evolutionary Behavior Tool for Reactive Multi-agent Systems
SBIA '02 Proceedings of the 16th Brazilian Symposium on Artificial Intelligence: Advances in Artificial Intelligence
Machine Learning and Inductive Logic Programming for Multi-agent Systems
EASSS '01 Selected Tutorial Papers from the 9th ECCAI Advanced Course ACAI 2001 and Agent Link's 3rd European Agent Systems Summer School on Multi-Agent Systems and Applications
APT Agents: Agents That Are Adaptive, Predictable, and Timely
FAABS '00 Proceedings of the First International Workshop on Formal Approaches to Agent-Based Systems-Revised Papers
Revisiting Asimov's First Law: A Response to the Call to Arms
ATAL '01 Revised Papers from the 8th International Workshop on Intelligent Agents VIII
Lyapunov design for safe reinforcement learning
The Journal of Machine Learning Research
Reactivity and Safe Learning in Multi-Agent Systems
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Incremental Verification for On-the-Fly Controller Synthesis
Electronic Notes in Theoretical Computer Science (ENTCS)
Asimovian multiagents: applying laws of robotics to teams of humans and agents
ProMAS'06 Proceedings of the 4th international conference on Programming multi-agent systems
Safe learning with real-time constraints: a case study
IEA/AIE'10 Proceedings of the 23rd international conference on Industrial engineering and other applications of applied intelligent systems - Volume Part I
An abstraction-refinement approach to verification of artificial neural networks
CAV'10 Proceedings of the 22nd international conference on Computer Aided Verification
NeVer: a tool for artificial neural networks verification
Annals of Mathematics and Artificial Intelligence
LEARNING AND VERIFYING SAFETY CONSTRAINTS FOR PLANNERS IN A KNOWLEDGE-IMPOVERISHED SYSTEM
Computational Intelligence
Hi-index | 0.00 |
The goal of this research is to develop agents that are adaptive and predictable and timely. At first blush, these three requirements seem contradictory. For example, adaptation risks introducing undesirable side effects, thereby making agents' behavior less predictable. Furthermore, although formal verification can assist in ensuring behavioral predictability, it is known to be time-consuming. Our solution to the challenge of satisfying all three requirements is the following. Agents have finite-state automaton plans, which are adapted online via evolutionary learning (perturbation) operators. To ensure that critical behavioral constraints are always satisfied, agents' plans are first formally verified. They are then reverified after every adaptation. If reverification concludes that constraints are violated, the plans are repaired. The main objective of this paper is to improve the efficiency of reverification after learning, so that agents have a sufficiently rapid response time. We present two solutions: positive results that certain learning operators are a priori guaranteed to preserve useful classes of behavioral assurance constraints (which implies that no reverification is needed for these operators), and efficient incremental reverification algorithms for those learning operators that have negative a priori results.