Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing transfer approaches either explicitly computes the similarity between tasks or select appropriate source policies to provide guided explorations for the target task. However, how to directly optimize the target policy by alternatively utilizing knowledge from appropriate source policies without explicitly measuring the similarity is currently missing. In this paper, we propose a novel Policy Transfer Framework (PTF) to accelerate RL by taking advantage of this idea. Our framework learns when and which source policy is the best to reuse for the target policy and when to terminate it by modeling multi-policy transfer as the option learning problem. PTF can be easily combined with existing deep RL approaches. Experimental results show it significantly accelerates the learning process and surpasses state-of-the-art policy transfer methods in terms of learning efficiency and final performance in both discrete and continuous action spaces.

We see the growth of people analytics at first-hand at Insight222, where we are now working with over 60 global organisations to help them put people analytics at the centre of business. In tandem we have also created a digital learning academy with myHRfuture to upskill HR in digital and analytics. For the last six years I have collated and published a collection of the'best' articles of the preceding 12 months – see 2014, 2015, 2016 2017 and 2018, and following are my choices for the 50 best articles of 2019. Those who have read the previous annual collections may note that the number of articles that make the cut has steadily risen. This is partly down to my inability to prune down to 30 or 20 - although it was hard enough to get it down to 50! Mainly though this recognises the increased number, variety and quality of people analytics and data-driven HR material now being published, which is another indicator of progress in the field. I hope that the articles selected will act as a venerable resource library for those working, researching or interested in the people analytics space. That is certainly the intention. I have arranged the 50 articles into twelve topics: i) Driving business value, ii) the future of work, iii) the future of the HR function, iv) ethics and trust, v) employee experience, vi) strategic workforce planning, vii) ONA, viii) diversity and inclusion, ix) organisational culture, perspectives and case studies from people analytics leaders, x) retention, xi) assessment and xii) getting started, as well as highlighting a few of my own articles from 2019 at the end. I hope you enjoy the articles selected, and if you do, please subscribe to my weekly Digital HR Leaders newsletter. Ultimately, people analytics should be about creating value – for leaders, for managers and for the workforce. So, where better to start than with seven articles that collectively provide insights on how to create value and/or give examples of where organisations have created value from people analytics.

When it comes to digital transformation, humans--believe it or not--play an integral role. In fact, companies that make strong use of the combined human/machine workforce have a far greater chance of success in digital transformation. Accenture calls these combined people/bot workspaces "future systems" – systems that seamlessly integrate humans and robots to create business goals that are limitless, agile, and "radically human." I consider the companies that harness the power of humans and machines will be the ultimate winners of the future of work. The good news: these systems are already happening.

The Cabinet on Tuesday approved a bill to support companies to develop secure 5G mobile networks and drone technologies amid growing alarm among Tokyo policy-makers over the increasing influence of China's 5G technology. The bill will give companies which develop such technologies access to low-interest rate loans from government-affiliated financial institutions if their plans fulfill standards on cyber security. Companies that adopt 5G technologies can also get tax incentives if they meet standards set by the government, according to the bill. The government will submit the bill to the parliament and aims to bring it to effect around summer. The United States has been waging a campaign against Huawei Technologies Co, which Washington has warned could spy on customers for Beijing.

The goal of federated learning is to design algorithms in which several agents communicate with a central node, in a privacy-protecting manner, to minimize the average of their loss functions. In this approach, each node not only shares the required computational budget but also has access to a larger data set, which improves the quality of the resulting model. However, this method only develops a common output for all the agents, and therefore, does not adapt the model to each user data. This is an important missing feature especially given the heterogeneity of the underlying data distribution for various agents. In this paper, we study a personalized variant of the federated learning in which our goal is to find a shared initial model in a distributed manner that can be slightly updated by either a current or a new user by performing one or a few steps of gradient descent with respect to its own loss function. This approach keeps all the benefits of the federated learning architecture while leading to a more personalized model for each user. We show this problem can be studied within the Model-Agnostic Meta-Learning (MAML) framework. Inspired by this connection, we propose a personalized variant of the well-known Federated Averaging algorithm and evaluate its performance in terms of gradient norm for non-convex loss functions. Further, we characterize how this performance is affected by the closeness of underlying distributions of user data, measured in terms of distribution distances such as Total Variation and 1-Wasserstein metric.

Neural networks and tree ensembles are state-of-the-art learners, each with its unique statistical and computational advantages. We aim to combine these advantages by introducing a new layer for neural networks, composed of an ensemble of differentiable decision trees (a.k.a. soft trees). While differentiable trees demonstrate promising results in the literature, in practice they are typically slow in training and inference as they do not support conditional computation. We mitigate this issue by introducing a new sparse activation function for sample routing, and implement true conditional computation by developing specialized forward and backward propagation algorithms that exploit sparsity. Our efficient algorithms pave the way for jointly training over deep and wide tree ensembles using first-order methods (e.g., SGD). Experiments on 23 classification datasets indicate over 10x speed-ups compared to the differentiable trees used in the literature and over 20x reduction in the number of parameters compared to gradient boosted trees, while maintaining competitive performance. Moreover, experiments on CIFAR, MNIST, and Fashion MNIST indicate that replacing dense layers in CNNs with our tree layer reduces the test loss by 7-53% and the number of parameters by 8x. We provide an open-source TensorFlow implementation with a Keras API.

Calibration and equal error rates are fundamental conditions for algorithmic fairness that have been shown to conflict with each other, suggesting that they cannot be satisfied simultaneously. This paper shows that the two are in fact compatible and presents a method for reconciling them. In particular, we derive necessary and sufficient conditions for the existence of calibrated scores that yield classifications achieving equal error rates. We then present an algorithm that searches for the most informative score subject to both calibration and minimal error rate disparity. Applied empirically to credit lending, our algorithm provides a solution that is more fair and profitable than a common alternative that omits sensitive features.

We present a method for financial time series forecasting using representation learning techniques. Recent progress on deep autoregressive models has shown their ability to capture long-term dependencies of the sequence data. However, the shortage of available financial data for training will make the deep models susceptible to the overfitting problem. In this paper, we propose a neural-network-powered conditional mutual information (CMI) estimator for learning representations for the forecasting task. Specifically, we first train an encoder to maximize the mutual information between the latent variables and the label information conditioned on the encoded observed variables. Then the features extracted from the trained encoder are used to learn a subsequent logistic regression model for predicting time series movements. Our proposed estimator transforms the CMI maximization problem to a classification problem whether two encoded representations are sampled from the same class or not. This is equivalent to perform pairwise comparisons of the training datapoints, and thus, improves the generalization ability of the deep autoregressive model. Empirical experiments indicate that our proposed method has the potential to advance the state-of-the-art performance.

We designed a machine learning algorithm that identifies patterns between ESG profiles and financial performances for companies in a large investment universe. The algorithm consists of regularly updated sets of rules that map regions into the high-dimensional space of ESG features to excess return predictions. The final aggregated predictions are transformed into scores which allow us to design simple strategies that screen the investment universe for stocks with positive scores. By linking the ESG features with financial performances in a non-linear way, our strategy based upon our machine learning algorithm turns out to be an efficient stock picking tool, which outperforms classic strategies that screen stocks according to their ESG ratings, as the popular best-in-class approach. Our paper brings new ideas in the growing field of financial literature that investigates the links between ESG behavior and the economy. We show indeed that there is clearly some form of alpha in the ESG profile of a company, but that this alpha can be accessed only with powerful, non-linear techniques such as machine learning.

A Relational Markov Decision Process (RMDP) is a first-order representation to express all instances of a single probabilistic planning domain with possibly unbounded number of objects. Early work in RMDPs outputs generalized (instance-independent) first-order policies or value functions as a means to solve all instances of a domain at once. Unfortunately, this line of work met with limited success due to inherent limitations of the representation space used in such policies or value functions. Can neural models provide the missing link by easily representing more complex generalized policies, thus making them effective on all instances of a given domain? We present the first neural approach for solving RMDPs, expressed in the probabilistic planning language of RDDL. Our solution first converts an RDDL instance into a ground DBN. We then extract a graph structure from the DBN. We train a relational neural model that computes an embedding for each node in the graph and also scores each ground action as a function over the first-order action variable and object embeddings on which the action is applied. In essence, this represents a neural generalized policy for the whole domain. Given a new test problem of the same domain, we can compute all node embeddings using trained parameters and score each ground action to choose the best action using a single forward pass without any retraining. Our experiments on nine RDDL domains from IPPC demonstrate that neural generalized policies are significantly better than random and sometimes even more effective than training a state-of-the-art deep reactive policy from scratch.