Related papers: POETREE: Interpretable Policy Learning with Adapti…
We address the problem of learning a decision policy from observational data of past decisions in contexts with features and associated outcomes. The past policy maybe unknown and in safety-critical applications, such as medical decision…
Decision tree learning is increasingly being used for pointwise inference. Important applications include causal heterogenous treatment effects and dynamic policy decisions, as well as conditional quantile regression and design of…
This paper introduces a novel causal framework for multi-stage decision-making in natural language action spaces where outcomes are only observed after a sequence of actions. While recent approaches like Proximal Policy Optimization (PPO)…
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…
Policy compliance assessment is a fundamental task of evaluating whether an input case strictly complies with a set of human-defined rules, more generally known as policies. In practice, human experts follow a systematic, step-by-step…
Deep reinforcement learning agents are prone to goal misalignments. The black-box nature of their policies hinders the detection and correction of such misalignments, and the trust necessary for real-world deployment. So far, solutions…
Deep Learning based models are currently dominating most state-of-the-art solutions for disease prediction. Existing works employ RNNs along with multiple levels of attention mechanisms to provide interpretability. These deep learning…
The use of machine learning algorithms in finance, medicine, and criminal justice can deeply impact human lives. As a consequence, research into interpretable machine learning has rapidly grown in an attempt to better control and fix…
This work introduces a novel interpretable machine learning method called Mixture of Decision Trees (MoDT). It constitutes a special case of the Mixture of Experts ensemble architecture, which utilizes a linear model as gating function and…
Tree ensembles such as random forests and boosted trees are accurate but difficult to understand, debug and deploy. In this work, we provide the inTrees (interpretable trees) framework that extracts, measures, prunes and selects rules from…
Prototype-based methods use interpretable representations to address the black-box nature of deep learning models, in contrast to post-hoc explanation methods that only approximate such models. We propose the Neural Prototype Tree…
In healthcare there is a pursuit for employing interpretable algorithms to assist healthcare professionals in several decision scenarios. Following the Predictive, Descriptive and Relevant (PDR) framework, the definition of interpretable…
We propose a method to capture the handling abilities of fast jet pilots in a software model via reinforcement learning (RL) from human preference feedback. We use pairwise preferences over simulated flight trajectories to learn an…
This paper explores interpretability techniques for two of the most successful learning algorithms in medical decision-making literature: deep neural networks and random forests. We applied these algorithms in a real-world medical dataset…
An important factor in the practical implementation of optimization models is the acceptance by the intended users. This is influenced among other factors by the interpretability of the solution process. Decision rules that meet this…
Many chemical engineering systems are governed by mechanisms that switch across operating regimes, making the data-driven discovery of regime-dependent governing equations essential for predictive modeling, optimization, and control. We…
Reinforcement learning techniques achieved human-level performance in several tasks in the last decade. However, in recent years, the need for interpretability emerged: we want to be able to understand how a system works and the reasons…
Over the past decade, adaptive video streaming technology has witnessed significant advancements, particularly driven by the rapid evolution of deep learning techniques. However, the black-box nature of deep learning algorithms presents…
We introduce a new preference-based framework for conditional treatment effect estimation and policy learning, built on the Conditional Preference-based Treatment Effect (CPTE). CPTE requires only that outcomes be ranked under a preference…
In many settings, a decision-maker wishes to learn a rule, or policy, that maps from observable characteristics of an individual to an action. Examples include selecting offers, prices, advertisements, or emails to send to consumers, as…