Interpretable Reinforcement Learning with Ensemble Methods
This addresses the need for interpretable AI solutions in reinforcement learning, though it is incremental by applying existing interpretable methods to this domain.
The paper tackled the problem of interpretability in reinforcement learning by using boosted regression trees, achieving solutions that are both interpretable and match the quality of leading methods.
We propose to use boosted regression trees as a way to compute human-interpretable solutions to reinforcement learning problems. Boosting combines several regression trees to improve their accuracy without significantly reducing their inherent interpretability. Prior work has focused independently on reinforcement learning and on interpretable machine learning, but there has been little progress in interpretable reinforcement learning. Our experimental results show that boosted regression trees compute solutions that are both interpretable and match the quality of leading reinforcement learning methods.