Designing Interpretable Approximations to Deep Reinforcement Learning
arXiv:2010.14785
Abstract
In an ever expanding set of research and application areas, deep neural networks (DNNs) set the bar for algorithm performance. However, depending upon additional constraints such as processing power and execution time limits, or requirements such as verifiable safety guarantees, it may not be feasible to actually use such high-performing DNNs in practice. Many techniques have been developed in recent years to compress or distill complex DNNs into smaller, faster or more understandable models and controllers. This work seeks to identify reduced models that not only preserve a desired performance level, but also, for example, succinctly explain the latent knowledge represented by a DNN. We illustrate the effectiveness of the proposed approach on the evaluation of decision tree variants and kernel machines in the context of benchmark reinforcement learning tasks.
References in corpus (8)
- Distilling the Knowledge in a Neural Network
- Playing Atari with Deep Reinforcement Learning
- Do Deep Nets Really Need to be Deep?
- Distilling a Neural Network Into a Soft Decision Tree
- Model compression via distillation and quantization
- Verifiable Reinforcement Learning via Policy Extraction
- Interpretability via Model Extraction
- Kickstarting Deep Reinforcement Learning