One important goal in sequential decision making problems is to construct a policy that maximizes the average reward over a certain amount of the time. Depending on the purpose of applications, the duration of the learned policy for use in the future (i.e., the planning horizon) is often unknown and can be different from what we consider in the stage of policy optimization. In addition, the performance measure used in learning the policy often depends on the choice of the initial state's distribution. It is always of a great interest to learn a policy with strong generalizability and adaptivity. Given a pre-collected data of multiple trajectories consisting of states, actions and rewards, our goal is to learn a robust policy in the sense that it can guarantee the uniform performance over the unknown planning horizon and the distributional change in the initial state.

We previously proposed a method that allows for nonparallel voice conversion (VC) by using a variant of generative adversarial networks (GANs) called StarGAN. The main features of our method, called StarGAN-VC, are as follows: First, it requires no parallel utterances, transcriptions, or time alignment procedures for speech generator training. Second, it can simultaneously learn mappings across multiple domains using a single generator network and thus fully exploit available training data collected from multiple domains to capture latent features that are common to all the domains. Third, it can generate converted speech signals quickly enough to allow real-time implementations and requires only several minutes of training examples to generate reasonably realistic-sounding speech. In this paper, we describe three formulations of StarGAN, including a newly introduced novel StarGAN variant called "Augmented classifier StarGAN (A-StarGAN)", and compare them in a nonparallel VC task. We also compare them with several baseline methods.

Temporal point process (TPP) models combined with recurrent neural networks provide a powerful framework for modeling continuous-time event data. While such models are flexible, they are inherently sequential and therefore cannot benefit from the parallelism of modern hardware. By exploiting the recent developments in the field of normalizing flows, we design TriTPP -- a new class of non-recurrent TPP models, where both sampling and likelihood computation can be done in parallel. TriTPP matches the flexibility of RNN-based methods but permits orders of magnitude faster sampling. This enables us to use the new model for variational inference in continuous-time discrete-state systems. We demonstrate the advantages of the proposed framework on synthetic and real-world datasets.

Activity recognition using built-in sensors in smart and wearable devices provides great opportunities to understand and detect human behavior in the wild and gives a more holistic view of individuals' health and well being. Numerous computational methods have been applied to sensor streams to recognize different daily activities. However, most methods are unable to capture different layers of activities concealed in human behavior. Also, the performance of the models starts to decrease with increasing the number of activities. This research aims at building a hierarchical classification with Neural Networks to recognize human activities based on different levels of abstraction. We evaluate our model on the Extrasensory dataset; a dataset collected in the wild and containing data from smartphones and smartwatches. We use a two-level hierarchy with a total of six mutually exclusive labels namely, "lying down", "sitting", "standing in place", "walking", "running", and "bicycling" divided into "stationary" and "non-stationary". The results show that our model can recognize low-level activities (stationary/non-stationary) with 95.8% accuracy and overall accuracy of 92.8% over six labels. This is 3% above our best performing baseline.

Inspired by the developments in deep generative models, we propose a model-based RL approach, coined Reinforced Deep Markov Model (RDMM), designed to integrate desirable properties of a reinforcement learning algorithm acting as an automatic trading system. The network architecture allows for the possibility that market dynamics are partially visible and are potentially modified by the agent's actions. The RDMM filters incomplete and noisy data, to create better-behaved input data for RL planning. The policy search optimisation also properly accounts for state uncertainty. Due to the complexity of the RKDF model architecture, we performed ablation studies to understand the contributions of individual components of the approach better. To test the financial performance of the RDMM we implement policies using variants of Q-Learning, DynaQ-ARIMA and DynaQ-LSTM algorithms. The experiments show that the RDMM is data-efficient and provides financial gains compared to the benchmarks in the optimal execution problem. The performance improvement becomes more pronounced when price dynamics are more complex, and this has been demonstrated using real data sets from the limit order book of Facebook, Intel, Vodafone and Microsoft.

Can an asset manager plan the optimal timing for her/his hedging strategies given market conditions? The standard approach based on Markowitz or other more or less sophisticated financial rules aims to find the best portfolio allocation thanks to forecasted expected returns and risk but fails to fully relate market conditions to hedging strategies decision. In contrast, Deep Reinforcement Learning (DRL) can tackle this challenge by creating a dynamic dependency between market information and hedging strategies allocation decisions. In this paper, we present a realistic and augmented DRL framework that: (i) uses additional contextual information to decide an action, (ii) has a one period lag between observations and actions to account for one day lag turnover of common asset managers to rebalance their hedge, (iii) is fully tested in terms of stability and robustness thanks to a repetitive train test method called anchored walk forward training, similar in spirit to k fold cross validation for time series and (iv) allows managing leverage of our hedging strategy. Our experiment for an augmented asset manager interested in sizing and timing his hedges shows that our approach achieves superior returns and lower risk.

We present a probabilistic programmed deep kernel learning approach to personalized, predictive modeling of neurodegenerative diseases. Our analysis considers a spectrum of neural and symbolic machine learning approaches, which we assess for predictive performance and important medical AI properties such as interpretability, uncertainty reasoning, data-efficiency, and leveraging domain knowledge. Our Bayesian approach combines the flexibility of Gaussian processes with the structural power of neural networks to model biomarker progressions, without needing clinical labels for training. We run evaluations on the problem of Alzheimer's disease prediction, yielding results surpassing deep learning and with the practical advantages of Bayesian non-parametrics and probabilistic programming.

Model-free reinforcement learning (MFRL) has achieved great success in game playing [1, 2], robot navigation [3, 4] and etc. However, extending existing RL methods to real-world environments remains challenging, because they require long-horizon reasoning with the low-dimensional useful features, e.g., the position of a robot, embedded in high-dimensional complex observations, e.g., visually rich images. Consider a four-legged mini-cheetah robot [5] navigating on the campus. To determine the traversable path, the robot must extract the relevant geometric features that coexist with irrelevant variable backgrounds, such as the moving pedestrians, paintings on the wall, etc. Model-based RL (MBRL), in contrast to the model-free methods, reasons a world model trained by generative learning and greatly improves the sample efficiency of the model-free methods [6, 7, 8]. Recent MBRL methods learn compact latent world models from high-dimensional visual inputs with Variational Autoencoders (VAEs) [9] by optimizing the evidence lower bound (ELBO) of an observation sequence [10, 11]. However, learning a generative model under complex observations is challenging.

We consider the problem of interactive partially observable Markov decision processes (I-POMDPs), where the agents are located at the nodes of a communication network. Specifically, we assume a certain message type for all messages. Moreover, each agent makes individual decisions based on the interactive belief states, the information observed locally and the messages received from its neighbors over the network. Within this setting, the collective goal of the agents is to maximize the globally averaged return over the network through exchanging information with their neighbors. We propose a decentralized belief propagation algorithm for the problem, and prove the convergence of our algorithm. Finally we show multiple applications of our framework. Our work appears to be the first study of decentralized belief propagation algorithm for networked multi-agent I-POMDPs.

In this paper we consider infinite horizon discounted dynamic programming problems with finite state and control spaces, partial state observations, and a multiagent structure. We discuss and compare algorithms that simultaneously or sequentially optimize the agents' controls by using multistep lookahead, truncated rollout with a known base policy, and a terminal cost function approximation. Our methods specifically address the computational challenges of partially observable multiagent problems. In particular: 1) We consider rollout algorithms that dramatically reduce required computation while preserving the key cost improvement property of the standard rollout method. The per-step computational requirements for our methods are on the order of $O(Cm)$ as compared with $O(C^m)$ for standard rollout, where $C$ is the maximum cardinality of the constraint set for the control component of each agent, and $m$ is the number of agents. 2) We show that our methods can be applied to challenging problems with a graph structure, including a class of robot repair problems whereby multiple robots collaboratively inspect and repair a system under partial information. 3) We provide a simulation study that compares our methods with existing methods, and demonstrate that our methods can handle larger and more complex partially observable multiagent problems (state space size $10^{37}$ and control space size $10^{7}$, respectively). Finally, we incorporate our multiagent rollout algorithms as building blocks in an approximate policy iteration scheme, where successive rollout policies are approximated by using neural network classifiers. While this scheme requires a strictly off-line implementation, it works well in our computational experiments and produces additional significant performance improvement over the single online rollout iteration method.