Soft Actor-Critic (SAC) [10, 11] is an off-policy actor-critic deep reinforcement learning (DRL) algorithm based on maximum entropy reinforcement learning. By combining off-policy updates with an actor-critic formulation, SAC achieves state-of-the-art performance on a range of continuous-action benchmark tasks, outperforming prior on-policy and off-policy methods. The off-policy method employed by SAC samples data uniformly from past experience when performing parameter updates. We propose Emphasizing Recent Experience (ERE), a simple but powerful off-policy sampling technique, which emphasizes recently observed data while not forgetting the past. The ERE algorithm samples more aggressively from recent experience, and also orders the updates to ensure that updates from old data do not overwrite updates from new data. We compare vanilla SAC and SAC ERE, and show that ERE is more sample efficient than vanilla SAC for continuous-action Mujoco tasks [31]. We also consider combining SAC with Priority Experience Replay (PER) [28], a scheme originally proposed for deep Q-learning which prioritizes the data based on temporal-difference (TD) error. We show that SAC PER can marginally improve the sample efficiency performance of SAC, but much less so than SAC ERE. Finally, we propose an algorithm which integrates ERE and PER and show that this hybrid algorithm can give the best results for some of the Mujoco tasks.

Flows based on either coupling or autoregressive transforms both offer exact density evaluation and sampling, but rely on the parameterization of an easily invertible elementwise transformation, whose choice determines the flexibility of these models. Building upon recent work, we propose a fully-differentiable module based on monotonic rational-quadratic splines, which enhances the flexibility of both coupling and autoregressive transforms while retaining analytic invertibility. We demonstrate that neural spline flows improve density estimation, variational inference, and generative modeling of images.

We consider the problem of functional matrix factorization, finding low-dimensional structure in a matrix where every entry is a noisy function evaluated at a set of discrete points. Such problems arise frequently in drug discovery, where biological samples form the rows, candidate drugs form the columns, and entries contain the dose-response curve of a sample treated at different concentrations of a drug. We propose Bayesian Tensor Filtering (BTF), a hierarchical Bayesian model of matrices of functions. BTF captures the smoothness in each individual function while also being locally adaptive to sharp discontinuities. The BTF model is agnostic to the likelihood of the underlying observations, making it flexible enough to handle many different kinds of data. We derive efficient Gibbs samplers for three classes of likelihoods: (i) Gaussian, for which updates are fully conjugate; (ii) Binomial and related likelihoods, for which updates are conditionally conjugate through P{\'o}lya--Gamma augmentation; and (iii) Black-box likelihoods, for which updates are non-conjugate but admit an analytic truncated elliptical slice sampling routine. We compare BTF against a state-of-the-art method for dynamic Poisson matrix factorization, showing BTF better reconstructs held out data in synthetic experiments. Finally, we build a dose-response model around BTF and show on real data from a multi-sample, multi-drug cancer study that BTF outperforms the current standard approach in biology. Code for BTF is available at https://github.com/tansey/functionalmf.

The space of Artificial Intelligence entities is dominated by conversational bots. Some of them fit in our pockets and we take them everywhere we go, or allow them to be a part of human homes. Siri, Alexa, they are recognised as present in our world. But a lot of games research is restricted to existing in the separate realm of software. We enter different worlds when playing games, but those worlds cease to exist once we quit. Similarly, AI game-players are run once on a game (or maybe for longer periods of time, in the case of learning algorithms which need some, still limited, period for training), and they cease to exist once the game ends. But what if they didn't? What if there existed artificial game-players that continuously played games, learned from their experiences and kept getting better? What if they interacted with the real world and us, humans: live-streaming games, chatting with viewers, accepting suggestions for strategies or games to play, forming opinions on popular game titles? In this paper, we introduce the vision behind a new project called Thyia, which focuses around creating a present, continuous, `always-on', interactive game-player.

Word count: 4980 Abstract Purpose: To accelerate MR scan, this paper incorporates deep learning into fast MR imaging by exploiting deep residual neural network with complex convolution for parallel MR image (DeepMRI) reconstruction from undersampled multi-coil measurements. Methods: DeepMRI draws and utilizes prior knowledge from a large number of existing fullysampled multi-coil measurements for accurate online fast imaging. It designs and trains an offline deep residual convolutional neural network to describe the mapping relationship between the MR images reconstructed from the undersampled and fully-sampled k-space data. Specifically, complex convolution was proposed to consider the intercorrelation between the real and imaginary parts. Furthermore, both k-space data fidelity and image space proximity are considered for the network training. Results: The evaluations on in vivo datasets show that the proposed DeepMRI has strong capability in capturing image information that are lost in the zero-filled MR images. The comparison with the classical SPIRiT and L1-SPIRiT has demonstrated that DeepMRI can reconstruct MR images more accurately.

Many circumstances of practical importance have performance or success metrics which exist implicitly---in the eye of the beholder, so to speak. Tuning aspects of such problems requires working without defined metrics and only considering pairwise comparisons or rankings. In this paper, we review an existing Bayesian optimization strategy for determining most-preferred outcomes, and identify an adaptation to allow it to handle ties. We then discuss some of the issues we have encountered when humans use this optimization strategy to optimize coloring a piece of abstract artwork. We hope that, by participating in this workshop, we can learn how other researchers encounter difficulties unique to working with humans in the loop.

Depression and anxiety are critical public health issues affecting millions of people around the world. To identify individuals who are vulnerable to depression and anxiety, predictive models have been built that typically utilize data from one source. Unlike these traditional models, in this study, we leverage a rich heterogeneous data set from the University of Notre Dame's NetHealth study that collected individuals' (student participants') social interaction data via smartphones, health-related behavioral data via wearables (Fitbit), and trait data from surveys. To integrate the different types of information, we model the NetHealth data as a heterogeneous information network (HIN). Then, we redefine the problem of predicting individuals' mental health conditions (depression or anxiety) in a novel manner, as applying to our HIN a popular paradigm of a recommender system (RS), which is typically used to predict the preference that a person would give to an item (e.g., a movie or book). In our case, the items are the individuals' different mental health states. We evaluate three state-of-the-art RS approaches. Also, we model the prediction of individuals' mental health as another problem type -- that of node classification (NC) in our HIN, evaluating in the process four node features under logistic regression as a proof-of-concept classifier. We find that our RS and NC network methods produce more accurate predictions than a logistic regression model using the same NetHealth data in the traditional non-network fashion as well as a random-approach. Also, we find that RS outperforms NC. This is the first study to integrate smartphone, wearable sensor, and survey data in an HIN manner and use RS or NC on the HIN to predict individuals' mental health conditions.

We present a new research task and a dataset to understand human social interactions via computational methods, to ultimately endow machines with the ability to encode and decode a broad channel of social signals humans use. This research direction is essential to make a machine that genuinely communicates with humans, which we call Social Artificial Intelligence. We first formulate the "social signal prediction" problem as a way to model the dynamics of social signals exchanged among interacting individuals in a data-driven way. We then present a new 3D motion capture dataset to explore this problem, where the broad spectrum of social signals (3D body, face, and hand motions) are captured in a triadic social interaction scenario. Baseline approaches to predict speaking status, social formation, and body gestures of interacting individuals are presented in the defined social prediction framework.

A graphical model is a structured representation of the data generating process. The traditional method to reason over random variables is to perform inference in this graphical model. However, in many cases the generating process is only a poor approximation of the much more complex true data generating process, leading to suboptimal estimation. The subtleties of the generative process are however captured in the data itself and we can "learn to infer", that is, learn a direct mapping from observations to explanatory latent variables. In this work we propose a hybrid model that combines graphical inference with a learned inverse model, which we structure as in a graph neural network, while the iterative algorithm as a whole is formulated as a recurrent neural network. By using cross-validation we can automatically balance the amount of work performed by graphical inference versus learned inference. We apply our ideas to the Kalman filter, a Gaussian hidden Markov model for time sequences, and show, among other things, that our model can estimate the trajectory of a noisy chaotic Lorenz Attractor much more accurately than either the learned or graphical inference run in isolation.

Classification on imbalanced datasets is a challenging task in real-world applications. Training conventional classification algorithms directly by minimizing classification error in this scenario can compromise model performance for minority class while optimizing performance for majority class. Traditional approaches to the imbalance problem include re-sampling and cost-sensitive methods. In this paper, we propose a neural network model with novel loss function, CRCEN, for imbalanced classification. Based on the weighted version of cross entropy loss, we provide a theoretical relation for model predicted probability, imbalance ratio and the weighting mechanism. To demonstrate the effectiveness of our proposed model, CRCEN is tested on several benchmark datasets and compared with baseline models.