AIBullisharXiv – CS AI · Jun 197/10
🧠
Human-like autonomy emerges from self-play and a pinch of human data
Researchers have developed a self-play reinforcement learning method that trains autonomous driving policies using only 30 minutes of human demonstrations alongside simulated self-play, achieving 2500x efficiency gains over traditional imitation learning approaches. The technique enables policies to align with human driving conventions while training in 15 hours on consumer-grade hardware, addressing a critical limitation in autonomous systems where pure simulation-trained agents develop incompatible behavioral patterns.