To Go or Not to Go: A Case for Q-Learning at Unsignalized Intersections

Autonomous driving at intersections with traffic lights and stop signs can be handled by simple rules, however unsignalized intersections remain a challenging problem. We explore the effectiveness of using Deep Q Networks to handle such problems. Combining several recent advances in Deep RL, were we able to learn policies that surpass the performance of a commonly-used rule based approach in several metrics including task completion time and goal success rate. Although the results were promising, the fact that learned policies resulted in collisions, although rarely, suggest a need for further research.