BehaviorBench reveals that self-play RL policies for autonomous driving overfit to their training traffic agents and do not generalize to other behaviors, motivating a hybrid rule-based plus learned planner.
Yuan Yin, Pegah Khayatan, Éloi Zablocki, Alexandre Boulch, and Matthieu Cord
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving
BehaviorBench reveals that self-play RL policies for autonomous driving overfit to their training traffic agents and do not generalize to other behaviors, motivating a hybrid rule-based plus learned planner.