A Unified Framework for Planning in Adversarial and Cooperative Environments
Open Access
- 17 July 2019
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 33 (01) , 2479-2487
Abstract
Users of AI systems may rely upon them to produce plans for achieving desired objectives. Such AI systems should be able to compute obfuscated plans whose execution in adversarial situations protects privacy, as well as legible plans which are easy for team members to understand in cooperative situations. We develop a unified framework that addresses these dual problems by computing plans with a desired level of comprehensibility from the point of view of a partially informed observer. For adversarial settings, our approach produces obfuscated plans with observations that are consistent with at least k goals from a set of decoy goals. By slightly varying our framework, we present an approach for producing legible plans in cooperative settings such that the observation sequence projected by the plan is consistent with at most j goals from a set of confounding goals. In addition, we show how the observability of the observer can be controlled to either obfuscate or convey the actions in a plan when the goal is known to the observer. We present theoretical results on the complexity analysis of our approach. We also present an empirical evaluation to show the feasibility and usefulness of our approaches using IPC domains.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Plan Explanations as Model Reconciliation: Moving Beyond Explanation as Soliloquy2017
- Stronger Privacy Preserving Projections for Multi-Agent PlanningProceedings of the International Conference on Automated Planning and Scheduling, 2016
- Goal Recognition Design with Non-Observable ActionsProceedings of the AAAI Conference on Artificial Intelligence, 2016
- Goal Recognition Design for Non-Optimal AgentsProceedings of the AAAI Conference on Artificial Intelligence, 2015
- Belief Tracking for Planning with Sensing: Width, Complexity and ApproximationsJournal of Artificial Intelligence Research, 2014
- A Concise Introduction to Models and Methods for Automated Planning2013
- Generating diverse plans to handle unknown and partially known user preferencesArtificial Intelligence, 2012
- Relationships between nondeterministic and deterministic tape complexitiesJournal of Computer and System Sciences, 1970