Optimal recovery of unsecured debt via interpretable reinforcement learning

This paper addresses the issue of interpretability and auditability of reinforcement-learning agents employed in the recovery of unsecured consumer debt. To this end, we develop a deterministic policy-gradient method that allows for a natural integration of domain expertise into the learning procedure so as to encourage learning of consistent, and thus interpretable, policies. Domain knowledge can often be expressed in terms of policy monotonicity and/or convexity with respect to relevant state inputs. We augment the standard actor–critic policy approximator using a monotonically regularized loss function which integrates domain expertise into the learning. Our formulation overcomes the challenge of learning interpretable policies by constraining the search to policies satisfying structural-consistency properties. The resulting state-feedback control laws can be readily understood and implemented by human decision makers. This new domain-knowledge enhanced learning approach is applied to the problem of optimal debt recovery which features a controlled Hawkes process and an asynchronous action–feedback relationship.

Learning to Reduce Annotation Load

Ksenia Konyushkova

Modern machine learning methods and their applications in computer vision are known to crave for large amounts of training data to reach their full potential. Because training data is mostly obtained through humans who manually label samples, it induces a significant cost. Therefore, the problem of reducing the annotation load is of great importance for the success of machine learning methods. We study the problem of reducing the annotation load from two viewpoints, by answering the questions âWhat to annotate?â and âHow to annotate?â. The question âWhat?â addresses the selection of a small portion of the data that would be sufficient to train an accurate model. The question âHow? focuses on minimising the effort of labelling each datapoint. The question âWhat to annotate?â becomes particularly compelling if we can select data to be annotated in an iterative and adaptive way, a setting known as active learning (AL). The key challenge in AL is to identify the datapoints that are the most informative for the model at a given stage. We propose several techniques to address this challenge. Firstly, we consider the problem of segmenting natural images and image volumes. We take advantage of image priors, such as smoothness of objects of interest, and use them in a novel form of geometric uncertainty. Using this, we design an AL technique to efficiently annotate data that is tailored to segmentation applications. Next, we notice that no single manually-designed strategy outperforms others in every application and that often the burden of designing new strategies outweighs the benefits of AL. To overcome this problem we suggest learning an AL strategy from data by formulating the AL problem as a regression task that predicts the reduction in the generalisation error achieved by labelling each datapoint. This enables us to learn AL strategies from simulated data and to transfer them to new datasets. Finally, we turn towards non-myopic data-driven AL strategies. To this end, we formulate the AL problem as a Markov decision process and find the best selection policy using reinforcement learning. We design the decision process such that the policy can be learnt for any ML model and transferred to diverse application domains. Effectively addressing the question âHow to annotate?â is of no less importance as large cost savings can be achieved by labelling each datapoint more efficiently. This can be done with intelligent interfaces that interact with a human annotator. We make two contributions towards answering the question âHow?â. Firstly, we propose an efficient technique to annotate 3D image volumes for image segmentation. Annotating data in 3D is cumbersome and an obvious way to facilitate it is to select a subset of the data lying on a 2D plane. To find the optimal plane (i.e. the one containing the most informative datapoints) we design a branch-and-bound algorithm that quickly eliminates hypotheses about the optimal projection. Secondly, we propose an intelligent data annotation method to train object detectors. Instead of always asking the human annotator to draw bounding boxes in images, we detect automatically in which cases we can rely on the current detector and verify its proposal.

EPFL2019

Learning continuous-time working memory tasks with on-policy neural reinforcement learning

Davide Zambrano

An animals' ability to learn how to make decisions based on sensory evidence is often well described by Reinforcement Learning (RL) frameworks. These frameworks, however, typically apply to event-based representations and lack the explicit and fine-grained notion of time needed to study psychophysically relevant measures like reaction times and psychometric curves. Here, we develop and use a biologically plausible continuous-time RL scheme of CT-AuGMEnT (Continuous-Time Attention-Gated MEmory Tagging) to study these behavioural quantities. We show how CT-AuGMEnT implements on-policy SARSA learning as a biologically plausible form of reinforcement learning with working memory units using 'attentional' feedback. We show that the CT-AuGMEnT model efficiently learns tasks in continuous time and can learn to accumulate relevant evidence through time. This allows the model to link task difficulty to psychophysical measurements such as accuracy and reaction-times. We further show how the implementation of a separate accessory network for feedback allows the model to learn continuously, also in case of significant transmission delays between the network's feedforward and feedback layers and even when the accessory network is randomly initialized. Our results demonstrate that CTAuGMEnT represents a fully time-continuous biologically plausible end-to-end RL model for learning to integrate evidence and make decisions. (c) 2021 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

2021

No-Regret Learning in Unknown Games with Correlated Payoffs

Ilija Bogunovic, Andreas Krause

We consider the problem of learning to play a repeated multi-agent game with an unknown reward function. Single player online learning algorithms attain strong regret bounds when provided with full information feedback, which unfortunately is unavailable in many real-world scenarios. Bandit feedback alone, i.e., observing outcomes only for the selected action, yields substantially worse performance. In this paper, we consider a natural model where, besides a noisy measurement of the obtained reward, the player can also observe the opponents' actions. This feedback model, together with a regularity assumption on the reward function, allows us to exploit the correlations among different game outcomes by means of Gaussian processes (GPs). We propose a novel confidence-bound based bandit algorithm GP-MW, which utilizes the GP model for the reward function and runs a multiplicative weight (MW) method. We obtain novel kernel-dependent regret bounds that are comparable to the known bounds in the full information setting, while substantially improving upon the existing bandit results. We experimentally demonstrate the effectiveness of GP-MW in random matrix games, as well as real-world problems of traffic routing and movie recommendation. In our experiments, GP-MW consistently outperforms several baselines, while its performance is often comparable to methods that have access to full information feedback.

Curran Associates, Inc.2019

Learning to Reduce Annotation Load

Ksenia Konyushkova

EPFL2019