Automatic Discovery of Interpretable Planning Strategies

05/24/2020
by   Julian Skirzynski, et al.
32

When making decisions, people often overlook critical information or are overly swayed by irrelevant information. A common approach to mitigate these biases is to provide decision-makers, especially professionals such as medical doctors, with decision aids, such as decision trees and flowcharts. Designing effective decision aids is a difficult problem. We propose that recently developed reinforcement learning methods for discovering clever heuristics for good decision-making can be partially leveraged to assist human experts in this design process. One of the biggest remaining obstacles to leveraging the aforementioned methods for improving human decision-making is that the policies they learn are opaque to people. To solve this problem, we introduce AI-Interpret: a general method for transforming idiosyncratic policies into simple and interpretable descriptions. Our algorithm combines recent advances in imitation learning and program induction with a new clustering method for identifying a large subset of demonstrations that can be accurately described by a simple, high-performing decision rule. We evaluate our new AI-Interpret algorithm and employ it to translate information-acquisition policies discovered through metalevel reinforcement learning. The results of three large behavioral experiments showed that the provision of decision rules as flowcharts significantly improved people's planning strategies and decisions across three different classes of sequential decision problems. Furthermore, a series of ablation studies confirmed that our AI-Interpret algorithm was critical to the discovery of interpretable decision rules and that it is ready to be applied to other reinforcement learning problems. We conclude that the methods and findings presented in this article are an important step towards leveraging automatic strategy discovery to improve human decision-making.

READ FULL TEXT

page 3

page 26

research
03/05/2022

Boosting human decision-making with AI-generated decision aids

Human decision-making is plagued by many systematic errors. Many of thes...
research
01/31/2021

Improving Human Decision-Making by Discovering Efficient Strategies for Hierarchical Planning

To make good decisions in the real world people need efficient planning ...
research
06/07/2020

Implications of Human Irrationality for Reinforcement Learning

Recent work in the behavioural sciences has begun to overturn the long-h...
research
09/29/2021

Automatic discovery and description of human planning strategies

Scientific discovery concerns finding patterns in data and creating insi...
research
06/14/2019

Personalized Apprenticeship Learning from Heterogeneous Decision-Makers

Human domain experts solve difficult planning problems by drawing on yea...
research
06/23/2023

Co-creating a globally interpretable model with human input

We consider an aggregated human-AI collaboration aimed at generating a j...
research
11/12/2017

Quickest Detection of Markov Networks

Detecting correlation structures in large networks arises in many domain...

Please sign up or login with your details

Forgot password? Click here to reset