Drawing an inspiration from behavioral studies of human decision making, we propose here a general parametric framework for a reinforcement learning problem, which extends the standard Q-learning approach to incorporate a two-stream framework of reward processing with biases biologically associated with several neurological and psychiatric conditions, including Parkinson's and Alzheimer's diseases, attention-deficit/hyperactivity disorder (ADHD), addiction, and chronic pain. For AI community, the development of agents that react differently to different types of rewards can enable us to understand a wide spectrum of multi-agent interactions in complex real-world socioeconomic systems. Moreover, from the behavioral modeling perspective, our parametric framework can be viewed as a first step towards a unifying computational model capturing reward processing abnormalities across multiple mental conditions and user preferences in long-term recommendation systems.

We consider the stochastic multi-armed bandit problem and the contextual bandit problem with historical observations and pre-clustered arms. The historical observations can contain any number of instances for each arm, and the pre-clustering information is a fixed clustering of arms provided as part of the input. We develop a variety of algorithms which incorporate this offline information effectively during the online exploration phase and derive their regret bounds. In particular, we develop the META algorithm which effectively hedges between two other algorithms: one which uses both historical observations and clustering, and another which uses only the historical observations. The former outperforms the latter when the clustering quality is good, and vice-versa. Extensive experiments on synthetic and real world datasets on Warafin drug dosage and web server selection for latency minimization validate our theoretical insights and demonstrate that META is a robust strategy for optimally exploiting the pre-clustering information.

We study the automated machine learning (AutoML) problem of jointly selecting appropriate algorithms from an algorithm portfolio as well as optimizing their hyper-parameters for certain learning tasks. The main challenges include a) the coupling between algorithm selection and hyper-parameter optimization (HPO), and b) the black-box optimization nature of the problem where the optimizer cannot access the gradients of the loss function but may query function values. To circumvent these difficulties, we propose a new AutoML framework by leveraging the alternating direction method of multipliers (ADMM) scheme. Due to the splitting properties of ADMM, algorithm selection and HPO can be decomposed through the augmented Lagrangian function. As a result, HPO with mixed continuous and integer constraints are efficiently handled through a query-efficient Bayesian optimization approach and Euclidean projection operator that yields a closed-form solution. Algorithm selection in ADMM is naturally interpreted as a combinatorial bandit problem. The effectiveness of our proposed methodology is compared to state-of-the-art AutoML schemes such as TPOT and Auto-sklearn on numerous benchmark data sets.

In recent years, multi-armed bandit (MAB) framework has attracted a lot of attention in various applications, from recommender systems and information retrieval to healthcare and finance, due to its stellar performance combined with certain attractive properties, such as learning from less feedback. The multi-armed bandit field is currently flourishing, as novel problem settings and algorithms motivated by various practical applications are being introduced, building on top of the classical bandit problem. This article aims to provide a comprehensive review of top recent developments in multiple real-life applications of the multi-armed bandit. Specifically, we introduce a taxonomy of common MAB-based applications and summarize state-of-art for each of those domains. Furthermore, we identify important current trends and provide new perspectives pertaining to the future of this exciting and fast-growing field.

Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings. Perhaps the most difficult of these settings is that of continual lifelong learning, where the model must learn online over a continuous stream of non-stationary data. A successful continual lifelong learning system must have three key capabilities: it must learn and adapt over time, it must not forget what it has learned, and it must be efficient in both training time and memory. Recent techniques have focused their efforts primarily on the first two capabilities while questions of efficiency remain largely unexplored. In this paper, we consider the problem of efficient and effective storage of experiences over very large time-frames. In particular we consider the case where typical experiences are O(n) bits and memories are limited to O(k) bits for k << n. We present a novel scalable architecture and training algorithm in this challenging domain and provide an extensive evaluation of its performance. Our results show that we can achieve considerable gains on top of state-of-the-art methods such as GEM.

Autonomous cyber-physical agents and systems play an increasingly large role in our lives. To ensure that agents behave in ways aligned with the values of the societies in which they operate, we must develop techniques that allow these agents to not only maximize their reward in an environment, but also to learn and follow the implicit constraints of society. These constraints and norms can come from any number of sources including regulations, business process guidelines, laws, ethical principles, social norms, and moral values. We detail a novel approach that uses inverse reinforcement learning to learn a set of unspecified constraints from demonstrations of the task, and reinforcement learning to learn to maximize the environment rewards. More precisely, we assume that an agent can observe traces of behavior of members of the society but has no access to the explicit set of constraints that give rise to the observed behavior. Inverse reinforcement learning is used to learn such constraints, that are then combined with a possibly orthogonal value function through the use of a contextual bandit-based orchestrator that picks a contextually-appropriate choice between the two policies (constraint-based and environment reward-based) when taking actions. The contextual bandit orchestrator allows the agent to mix policies in novel ways, taking the best actions from either a reward maximizing or constrained policy. In addition, the orchestrator is transparent on which policy is being employed at each time step. We test our algorithms using a Pac-Man domain and show that the agent is able to learn to act optimally, act within the demonstrated constraints, and mix these two functions in complex ways.

AI systems that learn through reward feedback about the actions they take are increasingly deployed in domains that have significant impact on our daily life. However, in many cases the online rewards should not be the only guiding criteria, as there are additional constraints and/or priorities imposed by regulations, values, preferences, or ethical principles. We detail a novel online agent that learns a set of behavioral constraints by observation and uses these learned constraints as a guide when making decisions in an online setting while still being reactive to reward feedback. To define this agent, we propose to adopt a novel extension to the classical contextual multi-armed bandit setting and we provide a new algorithm called Behavior Constrained Thompson Sampling (BCTS) that allows for online learning while obeying exogenous constraints. Our agent learns a constrained policy that implements the observed behavioral constraints demonstrated by a teacher agent, and then uses this constrained policy to guide the reward-based online exploration and exploitation. We characterize the upper bound on the expected regret of the contextual bandit algorithm that underlies our agent and provide a case study with real world data in two application domains. Our experiments show that the designed agent is able to act within the set of behavior constraints without significantly degrading its overall reward performance.

We propose a novel online algorithm for training deep feedforward neural networks that employs alternating minimization (block-coordinate descent) between the weights and activation variables. It extends off-line alternating minimization approaches to online, continual learning, and improves over stochastic gradient descent (SGD) with backpropagation in several ways: it avoids the vanishing gradient issue, it allows for non-differentiable nonlinearities, and it permits parallel weight updates across the layers. Unlike SGD, our approach employs co-activation memory inspired by the online sparse coding algorithm of [Mairal et al, 2009]. Furthermore, local iterative optimization with explicit activation updates is a potentially more biologically plausible learning mechanism than backpropagation. We provide theoretical convergence analysis and promising empirical results on several datasets.

We consider an extension of the contextual bandit setting, motivated by several practical applications, where an unlabeled history of contexts can become available for pre-training before the online decision-making begins. We propose an approach for improving the performance of contextual bandit in such setting, via adaptive, dynamic representation learning, which combines offline pre-training on unlabeled history of contexts with online selection and modification of embedding functions. Our experiments on a variety of datasets and in different nonstationary environments demonstrate clear advantages of our approach over the standard contextual bandit.

We consider a novel formulation of the multi-armed bandit model, which we call the contextual bandit with restricted context, where only a limited number of features can be accessed by the learner at every iteration. This novel formulation is motivated by different online problems arising in clinical trials, recommender systems and attention modeling. Herein, we adapt the standard multi-armed bandit algorithm known as Thompson Sampling to take advantage of our restricted context setting, and propose two novel algorithms, called the Thompson Sampling with Restricted Context(TSRC) and the Windows Thompson Sampling with Restricted Context(WTSRC), for handling stationary and nonstationary environments, respectively. Our empirical results demonstrate advantages of the proposed approaches on several real-life datasets