5 citations · 10 across the 8 of their papers we have counts for
6 papers · 1 filter
Learning Heterogeneous Preferences
Shiwali Mohan, Matt Hong, Dule Shu +3
Learning from human feedback has become a central paradigm for training modern AI systems, where models of human utility are used as reward models in policy learning. Existing meth…
Novelty Accommodating Multi-Agent Planning in High Fidelity Simulated Open World
James Chao, Wiktor Piotrowski, Roni Stern +4
Autonomous agents operating within real-world environments often rely on automated planners to ascertain optimal actions towards desired goals or the optimization of a specified ob…
A Domain-Independent Agent Architecture for Adaptive Operation in Evolving Open Worlds
Shiwali Mohan, Wiktor Piotrowski, Roni Stern +4
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. We propose HYDRA - a f…
Heuristic Search For Physics-Based Problems: Angry Birds in PDDL+
Wiktor Piotrowski, Yoni Sher, Sachin Grover +2
This paper studies how a domain-independent planner and combinatorial search can be employed to play Angry Birds, a well established AI challenge problem. To model the game, we use…
Learning to Operate in Open Worlds by Adapting Planning Models
Wiktor Piotrowski, Roni Stern, Yoni Sher +4
Planning agents are ill-equipped to act in novel situations in which their domain model no longer accurately represents the world. We introduce an approach for such agents operatin…
Playing Angry Birds with a Domain-Independent PDDL+ Planner
Wiktor Piotrowski, Roni Stern, Matthew Klenk +4
This demo paper presents the first system for playing the popular Angry Birds game using a domain-independent planner. Our system models Angry Birds levels using PDDL+, a planning…