# A Centralised Soft Actor Critic Deep Reinforcement Learning Approach to District Demand Side Management through CityLearn

arXiv: https://arxiv.org/abs/2009.10562 · HTML: https://mlsanity.com/paper/2009.10562/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2020.

## Built on by (most cited first, 7 of 7)

- [CityLearn v2: Energy-flexible, resilient, occupant-centric, and carbon-aware management of grid-interactive communities](https://mlsanity.com/paper/2405.03848/) (2024)
- [Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings](https://mlsanity.com/paper/2112.06127/) (2021)
- [Winning the CityLearn Challenge: Adaptive Optimization with Evolutionary Search under Trajectory-based Guidance](https://mlsanity.com/paper/2212.01939/) (2022)
- [MERLIN: Multi-agent offline and transfer learning for occupant-centric energy flexible operation of grid-interactive communities using smart meter data and CityLearn](https://mlsanity.com/paper/2301.01148/) (2022)
- [Development of a Soft Actor Critic Deep Reinforcement Learning Approach for Harnessing Energy Flexibility in a Large Office Building](https://mlsanity.com/paper/2104.12125/) (2021)
- [A Stochastic Online Forecast-and-Optimize Framework for Real-Time Energy Dispatch in Virtual Power Plants under Uncertainty](https://mlsanity.com/paper/2309.08642/) (2023)
- [Characterizing MARL for Energy Control: A Multi-KPI Benchmark on the CityLearn Environment](https://mlsanity.com/paper/2602.19223/) (2026)

## Abstract (arXiv)

Reinforcement learning is a promising model-free and adaptive controller for demand side management, as part of the future smart grid, at the district level. This paper presents the results of the algorithm that was submitted for the CityLearn Challenge, which was hosted in early 2020 with the aim of designing and tuning a reinforcement learning agent to flatten and smooth the aggregated curve of electrical demand of a district of diverse buildings. The proposed solution secured second place in the challenge using a centralised 'Soft Actor Critic' deep reinforcement learning agent that was able to handle continuous action spaces. The controller was able to achieve an averaged score of 0.967 on the challenge dataset comprising of different buildings and climates. This highlights the potential application of deep reinforcement learning as a plug-and-play style controller, that is capable of handling different climates and a heterogenous building stock, for district demand side management of buildings.