Heating and cooling systems in buildings account for 31% of global energy use, much of which are regulated by Rule Based Controllers (RBCs) that neither maximise energy efficiency nor minimise emissions by interacting optimally with the grid. Control via Reinforcement Learning (RL) has been shown to significantly improve building energy efficiency, but existing solutions require pre-training in simulators that are prohibitively expensive to obtain for every building in the world. In response, we show it is possible to perform safe, zero-shot control of buildings by combining ideas from system identification and model-based RL. We call this combination PEARL (Probabilistic Emission-Abating Reinforcement Learning) and show it reduces emissions without pre-training, needing only a three hour commissioning period. In experiments across three varied building energy simulations, we show PEARL outperforms an existing RBC once, and popular RL baselines in all cases, reducing building emissions by as much as 31% whilst maintaining thermal comfort.

翻译：建筑物的供暖和冷却系统占全球能源使用量的31%,其中大部分由基于规则的主计长(RCCs)管理,后者既不能最大限度地提高能源效率,也不能通过与电网进行最佳互动以最大限度地减少排放。 事实证明,通过强化学习(RL)进行控制可显著提高建筑能效,但现有的解决方案需要预先培训模拟器,这些模拟器价格高得令人望而却步,才能为世界上每一座建筑获取。 作为回应,我们通过整合系统识别和基于模型的RL的理念,表明可以对建筑物实施安全、零弹射控制。 我们称之为PEARL(安全排放减少强化学习)组合,并表明它无需培训即可减少排放,只需要三个小时的试运行期。 在三个不同的建筑能源模拟实验中,我们显示PEARL一次超越了现有的RBC, 在所有情况下都显示流行RL基线,在保持热舒适的同时将建筑排放量减少高达31 % 。