Model-based Reinforcement Learning from Signal Temporal Logic Specifications
This work addresses the problem of reward function design for robotic control, which is incremental as it applies existing STL and model-based methods to RL.
The paper tackles the challenge of designing reward functions for reinforcement learning in robotics by using Signal Temporal Logic (STL) specifications to encode desired high-level behavior, and it demonstrates the approach through simulations of robotic systems like a pick-and-place arm and adaptive cruise control.
Techniques based on Reinforcement Learning (RL) are increasingly being used to design control policies for robotic systems. RL fundamentally relies on state-based reward functions to encode desired behavior of the robot and bad reward functions are prone to exploitation by the learning agent, leading to behavior that is undesirable in the best case and critically dangerous in the worst. On the other hand, designing good reward functions for complex tasks is a challenging problem. In this paper, we propose expressing desired high-level robot behavior using a formal specification language known as Signal Temporal Logic (STL) as an alternative to reward/cost functions. We use STL specifications in conjunction with model-based learning to design model predictive controllers that try to optimize the satisfaction of the STL specification over a finite time horizon. The proposed algorithm is empirically evaluated on simulations of robotic system such as a pick-and-place robotic arm, and adaptive cruise control for autonomous vehicles.