TUPLES’ members papers at the 2023 ICAPS Conference
-
28/05/2023
-
NewsNews
Learned action policies π can be used to make real-time decisions in dynamic environments; one simply evaluates the policy on the current state in order to obtain the next action. Yet, this raises obvious concerns regarding potential policy “bugs”, that is, undesirable or even fatal policy behavior in particular situations. Testing – searching for bugs – is a natural paradigm to address these concerns.
A central component of action-policy testing are test oracles, which are responsible for recognizing states to be bugs. In the context of this paper, this means that, given a query state t, a test oracle attempts to establish that the behavior of π on t is sub-optimal. Recent work introduced metamorphic oracles realizing this by comparing the behavior of π on state pairs where one of the states is known to be easier to solve, i.e., if π performs better on a more difficult state s than on a simpler state t, then its behavior on t must be sub-optimal so that t must be a bug.
This paper shows how to automatically design such oracles based on simulation relations between states. It introduces two oracle families of this kind: first, morphing query states t to obtain suitable s; second, maintaining and comparing upper bounds on the cost of optimal plans for the states encountered during testing. Experiments show that these new oracles can find bugs much more quickly than the existing (search-based) alternatives and that the combination of the new oracles with search-based ones almost consistently dominates all other oracles.
You can view the paper here
The International Conference on Automated Planning and Scheduling (ICAPS) is the premier forum for exchanging news and research results on the theory and applications of intelligent and automated planning and scheduling technology. ICAPS 2023 is part of the ICAPS conference series. After three years of virtual events, ICAPS 2023 will be a physical conference again. ICAPS 2023 will be held July 8-13, 2023, in Prague, Czech Republic.
Latest News
At the World Conference on eXplainable AI (XAI) in Istanbul, TUPLES researchers Rebecca Eifler (LAAS-CNRS) and Guilhem Fouilhé (IRIT) presented IPEXCO, an innovative platform that brings humans and planners into dialogue through interactive goal-conflict explanations.
We’re proud to share that members of the TUPLES consortium — including Daniel Höller, Jörg Hoffmann, and our coordinator Sylvie Thiebaux — are on the organizing committee of the RIPL Workshop (Reliability in Planning and Learning), part of the prestigious ICAPS 2025 conference.
A recent article in the Czech magazine Nový Prostor, featuring our partners at the Faculty of Electrical Engineering at CVTU (Czech Technical University in Prague), offers a clear and accessible view of how TUPLES technology is already making a difference in urban waste collection — one of the project’s five real-world use cases.
Nearing the finish line of the TUPLES project, we’re reflecting on three years of ambitious, collaborative research into Trustworthy AI for Planning and Scheduling.
