可解释性
计算机科学
神经模糊
人工智能
灵活性(工程)
强化学习
模糊逻辑
人工神经网络
深度学习
航程(航空)
模糊控制系统
控制器(灌溉)
机器学习
工程类
数学
统计
航空航天工程
生物
农学
作者
Arne Gevaert,Jonathan Peck,Yvan Saeys
出处
期刊:Proceedings of ... IEEE International Conference on Fuzzy Systems
[Institute of Electrical and Electronics Engineers]
日期:2022-07-18
卷期号:: 1-8
被引量:8
标识
DOI:10.1109/fuzz-ieee55066.2022.9882791
摘要
Deep Reinforcement Learning uses a deep neural network to encode a policy, which achieves very good performance in a wide range of applications but is widely regarded as a black box model. A more interpretable alternative to deep networks is given by neuro-fuzzy controllers. Unfortunately, neuro-fuzzy controllers often need a large number of rules to solve relatively simple tasks, making them difficult to interpret. In this work, we present an algorithm to distill the policy from a deep Q-network into a compact neuro-fuzzy controller. This allows us to train compact neuro-fuzzy controllers through distillation to solve tasks that they are unable to solve directly, combining the flexibility of deep reinforcement learning and the interpretability of compact rule bases. We demonstrate the algorithm on three well-known environments from OpenAI Gym, where we nearly match the performance of a DQN agent using only 2 to 6 fuzzy rules.
科研通智能强力驱动
Strongly Powered by AbleSci AI