A4 Vertaisarvioitu artikkeli konferenssijulkaisussa

How to run a world record? A Reinforcement Learning approach




TekijätShahsavari Sajad, Immonen Eero, Karami Masoomeh, Haghbayan Mohammadhashem, Plosila Juha

ToimittajaIbrahim A. Hameed, Agus Hasan, Saleh Abdel-Afou Alaliyat

Konferenssin vakiintunut nimiEuropean Conference on Modelling and Simulation

KustantajaEuropean Council for Modelling and Simulation

Julkaisuvuosi2022

JournalProceedings: European Conference for Modelling and Simulation

Kokoomateoksen nimiProceedings of the 36th ECMS International Conference on Modelling and Simulation ECMS 2022 May 30th – June 3rd, 2022, Ålesund, Norway

Tietokannassa oleva lehden nimiProceedings - European Council for Modelling and Simulation, ECMS

Sarjan nimiProceedings : European Conference for Modelling and Simulation

Numero sarjassa36

Vuosikerta1

Aloitussivu159

Lopetussivu166

ISBN978-3-937436-77-7

ISSN2522-2414

eISSN2522-2422

Verkko-osoitehttps://www.scs-europe.net/dlib/2022/2022-0159.html

Rinnakkaistallenteen osoitehttps://research.utu.fi/converis/portal/detail/Publication/175657877


Tiivistelmä

Finding the optimal distribution of exerted effort by an athlete in competitive sports has been widely investigated in the fields of sport science, applied mathematics and optimal control. In this article, we propose a reinforcement learning-based solution to the optimal control problem in the running race application. Well-known mathematical model of Keller is used for numerically simulating the dynamics in runner's energy storage and motion. A feed-forward neural network is employed as the probabilistic controller model in continuous action space which transforms the current state (position, velocity and available energy) of the runner to the predicted optimal propulsive force that the runner should apply in the next time step. A logarithmic barrier reward function is designed to evaluate performance of simulated races as a continuous smooth function of runner's position and time. The neural network parameters, then, are identified by maximizing the expected reward using on-policy actor-critic policy-gradient RL algorithm. We trained the controller model for three race lengths: 400, 1500 and 10000 meters and found the force and velocity profiles that produce a near-optimal solution for the runner's problem. Results conform with Keller's theoretical findings with relative percent error of 0.59% and are comparable to real world records with relative percent error of 2.38%, while the same error for Keller's findings is 2.82%.


Ladattava julkaisu

This is an electronic reprint of the original article.
This reprint may differ from the original in pagination and typographic detail. Please cite the original version.





Last updated on 2024-26-11 at 11:52