Learning to Robustly Negotiate Bi-Directional Lane Usage in High-Conflict Driving Scenarios

no code implementations • 22 Mar 2021 • Christoph Killing, Adam Villaflor, John M. Dolan

We train policies to robustly negotiate with opposing vehicles of an unobservable degree of cooperativeness using multi-agent reinforcement learning (MARL).

Autonomous Driving Multi-agent Reinforcement Learning