Year: 2021
Type: preprint
Abstract: We address planning and navigation in challenging 3D video games featuring maps with disconnected regions reachable by agents using special actions. In this setting, classical symbolic planners are not applicable or difficult to adapt. We introduce a hybrid technique combining a low level policy trained with reinforcement learning and a graph based high level classical planner. In addition to providing human-interpretable paths, the approach improves the generalization performance of an end-to-end approach in unseen maps, where it achieves a 20% absolute increase in success rate over a recurrent end-to-end agent on a point to point navigation task in yet unseen large-scale maps of size 1km x 1km. In an in-depth experimental study, we quantify the limitations of end-to-end Deep RL approaches in vast environments and we also introduce "GameRLand3D", a new benchmark and soon to be released environment can generate complex procedural 3D maps for navigation tasks.
Source: arXiv (Cornell University)
Institutions: Institut national de recherche en sciences et technologies du numérique, Ubisoft (Canada), CHROMA: Robots coopératifs et adaptés à la présence humaine en environnements, Institut National des Sciences Appliquées de Lyon, Ubisoft (France), Centre National de la Recherche Scientifique, Université de Lyon, Laboratoire d'Informatique en Images et Systèmes d'Information
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4226203102