Bienhoff to defend master's thesis this week

Tyler Beinhoff will defend his dissertation and master's thesis this upcoming week.
Tyler Beinhoff will defend his dissertation and master's thesis this upcoming week.

Student Name: Tyler Bienhoff
Committee Members: Stephen Scott (advisor), Leen-Kiat Soh, Matthew Dwyer
Date: July 30, 2020
Time: 9:30 a.m.
Location: Zoom (

"Formal Language Constraints in Deep Reinforcement Learning for Self-Driving Vehicles"

Abstract: In recent years, self-driving vehicles have become a holy grail technology that, once fully developed, could radically change the daily behaviors of people and enhance safety. The complexities of controlling a car in a constantly changing environment are too immense to directly program how the vehicle should behave in each specific scenario. Thus, a common technique when developing autonomous vehicles is to use reinforcement learning, where vehicles can be trained in simulated and real-world environments to make proper decisions in a wide variety of scenarios. Reinforcement learning models, however, have uncertainties in how the vehicle acts, especially in a previously unseen situation that can lead to dangerous situations with humans onboard or nearby. To improve the safety of the agent, we propose formal language constraints that augment a standard reinforcement learning agent while being trained in a simulated self-driving environment. The constraints help the vehicle navigate turns and other situations by penalizing the agent when an action is chosen that could lead to a dangerous situation such as a collision. Empirically, we show that the agent, with these constraints, has a slight performance improvement as well as a significant decrease in collisions. Future work can expand upon the current constraints and evaluate using different reinforcement learning algorithms with constraints for training the self-driving agent.