TY - GEN
T1 - Go-Explore for Residential Energy Management
AU - Lu, Junlin
AU - Mannion, Patrick
AU - Mason, Karl
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2024
Y1 - 2024
N2 - Reinforcement learning is commonly applied in residential energy management, particularly for optimizing energy costs. However, RL agents often face challenges when dealing with deceptive and sparse rewards in the energy control domain, especially with stochastic rewards. In such situations, thorough exploration becomes crucial for learning an optimal policy. Unfortunately, the exploration mechanism can be misled by deceptive reward signals, making thorough exploration difficult. Go-Explore is a family of algorithms which combines planning methods and reinforcement learning methods to achieve efficient exploration. We use the Go-Explore algorithm to solve the cost-saving task in residential energy management problems and achieve an improvement of up to 19.84% compared to the well-known reinforcement learning algorithms.
AB - Reinforcement learning is commonly applied in residential energy management, particularly for optimizing energy costs. However, RL agents often face challenges when dealing with deceptive and sparse rewards in the energy control domain, especially with stochastic rewards. In such situations, thorough exploration becomes crucial for learning an optimal policy. Unfortunately, the exploration mechanism can be misled by deceptive reward signals, making thorough exploration difficult. Go-Explore is a family of algorithms which combines planning methods and reinforcement learning methods to achieve efficient exploration. We use the Go-Explore algorithm to solve the cost-saving task in residential energy management problems and achieve an improvement of up to 19.84% compared to the well-known reinforcement learning algorithms.
KW - Reinforcement Learning
KW - Residential Energy Management
UR - https://www.scopus.com/pages/publications/85184295982
U2 - 10.1007/978-3-031-50485-3_11
DO - 10.1007/978-3-031-50485-3_11
M3 - Conference Publication
AN - SCOPUS:85184295982
SN - 9783031504846
T3 - Communications in Computer and Information Science
SP - 133
EP - 139
BT - Artificial Intelligence. ECAI 2023 International Workshops - XAI^3, TACTIFUL, XI-ML, SEDAMI, RAAIT, AI4S, HYDRA, AI4AI 2023, Proceedings
A2 - Nowaczyk, Sławomir
A2 - Biecek, Przemysław
A2 - Chung, Neo Christopher
A2 - Vallati, Mauro
A2 - Skruch, Paweł
A2 - Jaworek-Korjakowska, Joanna
A2 - Parkinson, Simon
A2 - Nikitas, Alexandros
A2 - Atzmüller, Martin
A2 - Kliegr, Tomáš
A2 - Schmid, Ute
A2 - Bobek, Szymon
A2 - Lavrac, Nada
A2 - Peeters, Marieke
A2 - van Dierendonck, Roland
A2 - Robben, Saskia
A2 - Mercier-Laurent, Eunika
A2 - Kayakutlu, Gülgün
A2 - Owoc, Mieczyslaw Lech
A2 - Mason, Karl
A2 - Wahid, Abdul
A2 - Bruno, Pierangela
A2 - Calimeri, Francesco
A2 - Cauteruccio, Francesco
A2 - Terracina, Giorgio
A2 - Wolter, Diedrich
A2 - Leidner, Jochen L.
A2 - Kohlhase, Michael
A2 - Dimitrova, Vania
PB - Springer Science and Business Media Deutschland GmbH
T2 - International Workshops of the 26th European Conference on Artificial Intelligence, ECAI 2023
Y2 - 30 September 2023 through 4 October 2023
ER -