<ul><li>Tradable credit schemes (TCS) are an alternative to congestion pricing, addressing equity and revenue neutrality.</li><li>This paper focuses on the day-to-day dynamic tolling problem under TCS using reinforcement learning (RL).</li><li>RL algorithms achieve comparable travel times and social welfare, even with varying capacities and demand levels.</li><li>Challenges include scaling to large networks, but transfer learning can improve computational efficiency.</li></ul>

Deep Reinforcement Learning for Day-to-day Dynamic Tolling in Tradable Credit Schemes

Discover more