A Domain-Independent Agent Architecture for Adaptive Operation in Evolving Open Worlds

no code implementations • 9 Jun 2023 • Shiwali Mohan, Wiktor Piotrowski, Roni Stern, Sachin Grover, Sookyung Kim, Jacob Le, Johan de Kleer

Model-based reasoning agents are ill-equipped to act in novel situations in which their model of the environment no longer sufficiently represents the world.

Visual Reasoning

Learning to Operate in Open Worlds by Adapting Planning Models

no code implementations • 24 Mar 2023 • Wiktor Piotrowski, Roni Stern, Yoni Sher, Jacob Le, Matthew Klenk, Johan deKleer, Shiwali Mohan

Planning agents are ill-equipped to act in novel situations in which their domain model no longer accurately represents the world.

Reinforcement Learning (RL)

Playing Angry Birds with a Domain-Independent PDDL+ Planner

no code implementations • 9 Jul 2021 • Wiktor Piotrowski, Roni Stern, Matthew Klenk, Alexandre Perez, Shiwali Mohan, Johan de Kleer, Jacob Le

This demo paper presents the first system for playing the popular Angry Birds game using a domain-independent planner.