Adrian Till Assmuth
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Adrian Till Assmuth has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Benjamin Schäfer
Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology, Eggenstein-Leopoldshafen, Germany
2 shared publications - Felix Langner
Karlsruhe Institute of Technology, Karlsruhe, Germany
2 shared publications - Qiong Huang
Karlsruhe Institute of Technology, Karlsruhe, Germany
2 shared publications Veit Hagenmeyer
1 shared publication- Veit Hagenmeyer
Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology
1 shared publication
Latest Publications
- Open Access
- 22 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 42-54
Trans-SAC: Robust and Transferable Maximum Entropy Reinforcement Learning for Heat Pump Control
- 22 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 42-54
Open AccessTrans-SAC: Robust and Transferable Maximum Entropy Reinforcement Learning for Heat Pump Control
- Open Access
- 1 March 2026
- Published by Springer Nature in KI - Künstliche Intelligenz
- Vol. 40 (1) , 17-25
Deep Reinforcement Learning for Price-Aware Building Heating Control
Heating systems account for a significant share of residential energy consumption, and rising energy prices call for intelligent, cost-aware control strategies. Traditional methods, such as rule-based or model predictive control (MPC), often require detailed system modeling or lack adaptability to dynamic price signals. This work explores the use of deep reinforcement learning (DRL) to control heat pumps in a way that balances occupant comfort with energy-cost minimization. We evaluate deep Q-network (DQN) and proximal policy optimization (PPO) methods across discrete and continuous action spaces. The agents are trained in simulation using real weather and electricity price data, with a model representing the thermal dynamics of the building. Short-term electricity price forecasts are included to enable anticipatory heating strategies. Reward functions combine price penalties with piecewise-linear or quadratic comfort penalties. Among the DRL variants, a DQN agent with discrete actions and a piecewise-linear comfort reward achieves the best overall trade-off between comfort and cost. MPC still performs best in absolute cost terms because it uses an exact model, while the DQN policy approaches MPC performance and retains the model-free, adaptive advantages of RL. The findings highlight the potential of DRL for adaptive and price-aware heating control without the need for detailed physical modeling.
- 1 March 2026
- Published by Springer Nature in KI - Künstliche Intelligenz
- Vol. 40 (1) , 17-25
Open AccessDeep Reinforcement Learning for Price-Aware Building Heating Control
Heating systems account for a significant share of residential energy consumption, and rising energy prices call for intelligent, cost-aware control strategies. Traditional methods, such as rule-based or model predictive control (MPC), often require detailed system modeling or lack adaptability to dynamic price signals. This work explores the use of deep reinforcement learning (DRL) to control heat pumps in a way that balances occupant comfort with energy-cost minimization. We evaluate deep Q-network (DQN) and proximal policy optimization (PPO) methods across discrete and continuous action spaces. The agents are trained in simulation using real weather and electricity price data, with a model representing the thermal dynamics of the building. Short-term electricity price forecasts are included to enable anticipatory heating strategies. Reward functions combine price penalties with piecewise-linear or quadratic comfort penalties. Among the DRL variants, a DQN agent with discrete actions and a piecewise-linear comfort reward achieves the best overall trade-off between comfort and cost. MPC still performs best in absolute cost terms because it uses an exact model, while the DQN policy approaches MPC performance and retains the model-free, adaptive advantages of RL. The findings highlight the potential of DRL for adaptive and price-aware heating control without the need for detailed physical modeling.