# Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy Source: [Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy]() Collection index: [llms.txt]() Data updated: 2026-04-14T05:00:04.234Z Authors: Jung-Hoon Cho, Sirui Li, Jeongyun Kim, Cathy Wu Published: 2023-11-27T21:18:06.000Z ## Abstract The recent development of connected and automated vehicle (CAV) technologies has spurred investigations to optimize dense urban traffic to maximize vehicle speed and throughput. This paper explores advisory autonomy, in which real-time driving advisories are issued to the human drivers, thus achieving near-term performance of automated vehicles. Due to the complexity of traffic systems, recent studies of coordinating CAVs have resorted to leveraging deep reinforcement learning (RL). Coarse-grained advisory is formalized as zero-order holds, and we consider a range of hold duration from 0.1 to 40 seconds. However, despite the similarity of the higher frequency tasks on CAVs, a direct application of deep RL fails to be generalized to advisory autonomy tasks. To overcome this, we utilize zero-shot transfer, training policies on a set of source tasks--specific traffic scenarios with designated hold durations--and then evaluating the efficacy of these policies on different target tasks. We introduce Temporal Transfer Learning (TTL) algorithms to select source tasks for zero-shot transfer, systematically leveraging the temporal structure to solve the full range of tasks. TTL selects the most suitable source tasks to maximize the performance of the range of tasks. We validate our algorithms on diverse mixed-traffic scenarios, demonstrating that TTL more reliably solves the tasks than baselines. This paper underscores the potential of coarse-grained advisory autonomy with TTL in traffic flow optimization. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Traffic Management (Acceleration Guidance) on Single-Lane Ring](): Traffic Management (Acceleration Guidance); Single-Lane Ring; Average Speed (m/s): 4.04. - [Traffic Management (Acceleration Guidance) on Highway Ramp](): Traffic Management (Acceleration Guidance); Highway Ramp; Average Speed (m/s): 5.2. - [Traffic Management (Speed Guidance) on Single-Lane Ring](): Traffic Management (Speed Guidance); Single-Lane Ring; Average Speed (m/s): 4.4. - [Traffic Management (Speed Guidance) on Highway Ramp](): Traffic Management (Speed Guidance); Highway Ramp; Average Speed (m/s): 6.25. - [Traffic Management (Acceleration Guidance) on Signalized Intersection](): Traffic Management (Acceleration Guidance); Signalized Intersection; Average Speed (m/s): 7.71. - [Traffic Management (Speed Guidance) on Signalized Intersection](): Traffic Management (Speed Guidance); Signalized Intersection; Average Speed (m/s): 7.71. - [Traffic signal control on Traffic Signal Speed Limit variation](): Traffic Signal Control; Traffic Signal Speed Limit variation; Normalized Reward: 88.74. - [Advisory autonomy on Advisory Autonomy Highway ramp (Acceleration guidance)](): Advisory autonomy; Advisory Autonomy Highway ramp (Acceleration guidance); Normalized Reward: 0.657. - [Dynamic eco-driving on Eco-Driving Inflow variation](): Dynamic eco-driving; Eco-Driving Inflow variation; Normalized Reward: 0.5299. - [Advisory autonomy on Advisory Autonomy Single lane ring (Speed guidance)](): Advisory autonomy; Advisory Autonomy Single lane ring (Speed guidance); Normalized Reward: 0.9819. - [Advisory autonomy on Advisory Autonomy Highway ramp (Speed guidance)](): Advisory autonomy; Advisory Autonomy Highway ramp (Speed guidance); Normalized Reward: 64.61. - [Dynamic eco-driving on Eco-Driving Penetration Rate variation](): Dynamic eco-driving; Eco-Driving Penetration Rate variation; Normalized Reward: 0.5992. - [Dynamic eco-driving on Eco-Driving Green Phase variation](): Dynamic eco-driving; Eco-Driving Green Phase variation; Normalized Reward: 0.4678. - [Traffic Signal Control on Traffic Signal Inflow variation](): Traffic Signal Control; Traffic Signal Inflow variation; Normalized Reward: 0.8682. - [Advisory autonomy on Single lane ring (Acceleration guidance)](): Advisory autonomy; Advisory Autonomy Single lane ring (Acceleration guidance); Normalized Reward: 90.21. - [Traffic Signal Control on Traffic Signal Road Length variation](): Traffic Signal Control; Traffic Signal Road Length variation; Normalized Reward: 0.9349. ## Original sources and implementation [Original paper]() [PDF]()