What question did this study set out to answer?

To develop and evaluate a decision-making framework combining deep reinforcement learning with game-theoretic reasoning for autonomous vehicles executing left turns at unsignalized intersections.

August 15, 2026Transportation Research Record Journal of the Transportation Research Board

Left Turns at Unsignalized Intersections: Decision Making for Autonomous Vehicles Using Deep Reinforcement Learning with Game-Theoretic Reasoning

View Full Paper

Ask AI

Bookmark

To develop and evaluate a decision-making framework combining deep reinforcement learning with game-theoretic reasoning for autonomous vehicles executing left turns at unsignalized intersections.
Designed the DLT-GT framework integrating discrete strategic choices and continuous vehicle control with a risk-weighted payoff structure.
Implemented proximal policy optimization (PPO) as the stable reinforcement learning backbone to model multiagent interactions with vehicles and pedestrians.
Tested the framework using microscopic traffic simulations across varied traffic volumes, driver aggressiveness levels, and safety sensitivity thresholds.
Achieved zero collisions across all simulated intersection scenarios compared to a baseline reinforcement learning agent.
Demonstrated higher cumulative rewards, shorter maneuver completion times, and enhanced decision stability under diverse traffic conditions.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Simulation study reveals zero collisions and reduced maneuver times in autonomous left turns, indicating game-theoretic reinforcement learning improves complex multiagent decision-making.

Cite This Study

Hu et al. (2026) studied this question.

synapsesocial.com/papers/6a8019ce75c2e31742c85ef7 https://doi.org/10.1177/03611981261467318

View Full Paper

Ask AI

Bookmark

Implication

Simulation study reveals zero collisions and reduced maneuver times in autonomous left turns, indicating game-theoretic reinforcement learning improves complex multiagent decision-making.

Left Turns at Unsignalized Intersections: Decision Making for Autonomous Vehicles Using Deep Reinforcement Learning with Game-Theoretic Reasoning

Key Points

Discussion

Implication

Cite This Study

Left Turns at Unsignalized Intersections: Decision Making for Autonomous Vehicles Using Deep Reinforcement Learning with Game-Theoretic Reasoning

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider