2018/09/24 by Aleksandra Faust, James B. Aimone, Faust, Aleksandra +5 · 1 voice
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Computability, Logic, AI Algorithms #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Optimization and Search Problems #Reinforcement Learning in Robotics #Systems and Control (eess.SY) #cs.AI #cs.LG #eess.SY #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1809.09261
openalex publication_date 2018/09/24 · arxiv published 2018/09/25 · arxiv updated 2018/09/25 · openalex created_date 2022/08/03 · openalex updated_date 2026/07/28
Robots and autonomous agents often complete goal-based tasks with limited resources, relying on imperfect models and sensor measurements. In particular, reinforcement learning (RL) and feedback control can be used to help a robot achieve a goal. Taking advantage of this body of work, this paper formulates general computation as a feedback-control problem, which allows the agent to autonomously overcome some limitations of standard procedural language programming: resilience to errors and early program termination. Our formulation considers computation to be trajectory generation in the program's variable space. The computing then becomes a sequential decision making problem, solved with reinforcement learning (RL), and analyzed with Lyapunov stability theory to assess the agent's resilience and progression to the goal. We do this through a case study on a quintessential computer science problem, array sorting. Evaluations show that our RL sorting agent makes steady progress to an asymptotically stable goal, is resilient to faulty components, and performs less array manipulations than traditional Quicksort and Bubble sort.