We consider the problem of approximating the stationary distribution of an ergodic Markov chain given a set of sampled transitions. Classical simulation-based approaches assume access to the underlying process so that trajectories of sufficient length can be gathered to approximate stationary sampling. Instead, we consider an alternative setting where a fixed set of transitions has been collected beforehand, by a separate, possibly unknown procedure. The goal is still to estimate properties of the stationary distribution, but without additional access to the underlying system. We propose a consistent estimator that is based on recovering a correction ratio function over the given data. In particular, we develop a variational power method (VPM) that provides provably consistent estimates under general conditions. In addition to unifying a number of existing approaches from different subfields, we also find that VPM yields significantly better estimates across a range of problems, including queueing, stochastic differential equations, post-processing MCMC, and off-policy evaluation.

Rehabilitation assessment is critical to determine an adequate intervention for a patient. However, the current practices of assessment mainly rely on therapist's experience, and assessment is infrequently executed due to the limited availability of a therapist. In this paper, we identified the needs of therapists to assess patient's functional abilities (e.g. alternative perspective on assessment with quantitative information on patient's exercise motions). As a result, we developed an intelligent decision support system that can identify salient features of assessment using reinforcement learning to assess the quality of motion and summarize patient specific analysis. We evaluated this system with seven therapists using the dataset from 15 patient performing three exercises. The evaluation demonstrates that our system is preferred over a traditional system without analysis while presenting more useful information and significantly increasing the agreement over therapists' evaluation from 0.6600 to 0.7108 F1-scores ($p <0.05$). We discuss the importance of presenting contextually relevant and salient information and adaptation to develop a human and machine collaborative decision making system.

Social Reinforcement Learning methods, which model agents in large networks, are useful for fake news mitigation, personalized teaching/healthcare, and viral marketing, but it is challenging to incorporate inter-agent dependencies into the models effectively due to network size and sparse interaction data. Previous social RL approaches either ignore agents dependencies or model them in a computationally intensive manner. In this work, we incorporate agent dependencies efficiently in a compact model by clustering users (based on their payoff and contribution to the goal) and combine this with a method to easily derive personalized agent-level policies from cluster-level policies. We also propose a dynamic clustering approach that captures changing user behavior. Experiments on real-world datasets illustrate that our proposed approach learns more accurate policy estimates and converges more quickly, compared to several baselines that do not use agent correlations or only use static clusters.

To fully realize industrial automation, it is indispensable to give the robot manipulators the ability to adapt by themselves to their surroundings and to learn to handle novel manipulation tasks. Reinforcement Learning (RL) methods have been proven successful in solving manipulation tasks autonomously. However, RL is still not widely adopted on real robotic systems because working with real hardware entails additional challenges, especially when using rigid position-controlled manipulators. These challenges include the need for a robust controller to avoid undesired behavior, that risk damaging the robot and its environment, and constant supervision from a human operator. The main contributions of this work are, first, we propose a framework for safely training an RL agent on manipulation tasks using a rigid robot. Second, to enable a position-controlled manipulator to perform contact-rich manipulation tasks, we implemented two different force control schemes based on standard force feedback controllers; one is a modified hybrid position-force control, and the other one is an impedance control. Third, we empirically study both control schemes when used as the action representation of an RL agent. We evaluate the trade-off between control complexity and performance by comparing several versions of the control schemes, each with a different number of force control parameters. The proposed methods are validated both on simulation and a real robot, a UR3 e-series robotic arm when executing contact-rich manipulation tasks.

We study the Safe Reinforcement Learning (SRL) problem using the Constrained Markov Decision Process (CMDP) formulation in which an agent aims to maximize the expected total reward subject to a safety constraint on the expected total value of a criterion function (e.g., utility). We focus on an episodic setting with the function approximation where the reward and criterion functions and the Markov transition kernels all have a linear structure but do not impose any additional assumptions on the sampling model. Designing SRL algorithms with provable computational and statistical efficiency is particularly challenging under this setting because of the need to incorporate both the safety constraint and the function approximation into the fundamental exploitation/exploration tradeoff. To this end, we present an {O}ptimistic {P}rimal-{D}ual Proximal Policy {OP}timization (OPDOP) algorithm where the value function is estimated by combining the least-squares policy evaluation and an additional bonus term for safe exploration. We prove that the proposed algorithm achieves an O(d^{1.5}H^{3.5}\sqrt{T}) regret and an O(d^{1.5}H^{3.5}\sqrt{T}) constraint violation, where d is the dimension of the feature mapping, H is the horizon of each episode, and T is the total number of steps. We establish these bounds under the following two settings: (i) Both the reward and criterion functions can change adversarially but are revealed entirely after each episode. (ii) The reward/criterion functions are fixed but the feedback after each episode is bandit. Our bounds depend on the capacity of the state space only through the dimension of the feature mapping and thus our results hold even when the number of states goes to infinity. To the best of our knowledge, we provide the first provably efficient policy optimization algorithm for CMDPs with safe exploration.

The marriage of wireless big data and machine learning techniques revolutionizes the wireless system by the data-driven philosophy. However, the ever exploding data volume and model complexity will limit centralized solutions to learn and respond within a reasonable time. Therefore, scalability becomes a critical issue to be solved. In this article, we aim to provide a systematic discussion on the building blocks of scalable data-driven wireless networks. On one hand, we discuss the forward-looking architecture and computing framework of scalable data-driven systems from a global perspective. On the other hand, we discuss the learning algorithms and model training strategies performed at each individual node from a local perspective. We also highlight several promising research directions in the context of scalable data-driven wireless communications to inspire future research.

This paper proposes a \emph{fully asynchronous} scheme for policy evaluation of distributed reinforcement learning (DisRL) over peer-to-peer networks. Without any form of coordination, nodes can communicate with neighbors and compute their local variables using (possibly) delayed information at any time, which is in sharp contrast to the asynchronous gossip. Thus, the proposed scheme fully takes advantage of the distributed setting. We prove that our method converges at a linear rate $\mathcal{O}(c^k)$ where $c\in(0,1)$ and $k$ increases by one no matter on which node updates, showing the computational advantage by reducing the amount of synchronization. Numerical experiments show that our method speeds up linearly w.r.t. the number of nodes, and is robust to straggler nodes. To the best of our knowledge, our work is the first theoretical analysis for asynchronous update in DisRL, including the \emph{parallel RL} domain advocated by A3C.

Reinforcement learning and control consider the behavior of an agent making decisions in a dynamic environment in order to suffer minimal loss. In light of recent practical breakthroughs in datadriven approaches to continuous RL and control (Lillicrap et al., 2016; Mnih et al., 2015; Silver et al., 2017), there is great interest in applying these techniques in real-world decision making applications. However, to reliably deploy data-driven RL and control in physical systems such as self-driving cars, it is critical to develop principled algorithms with provable safety and robustness guarantees. At the same time, algorithms should not be overly pessimistic, and should be able to take advantage of benign environments whenever possible. In this paper we develop algorithms for online linear-quadratic control which ensure robust worst-case performance while optimally adapting to the environment at hand. Linear control has traditionally been studied in settings where the dynamics of the environment are either governed by a well-behaved stochastic process or driven by a worst-case process to which the learner must remain robust in theH sense. We consider an intermediate approach introduced by Agarwal et al. (2019a) in which disturbances are non-stochastic but performance is evaluated in terms of regret. This benchmark forces the learner's control policy to achieve near optimal performance on any specific disturbance process encountered.

A large portion of passenger requests is reportedly unserviced, partially due to vacant for-hire drivers' cruising behavior during the passenger seeking process. This paper aims to model the multi-driver repositioning task through a mean field multi-agent reinforcement learning (MARL) approach that captures competition among multiple agents. Because the direct application of MARL to the multi-driver system under a given reward mechanism will likely yield a suboptimal equilibrium due to the selfishness of drivers, this study proposes an reward design scheme with which a more desired equilibrium can be reached. To effectively solve the bilevel optimization problem with upper level as the reward design and the lower level as a multi-agent system, a Bayesian optimization (BO) algorithm is adopted to speed up the learning process. We then apply the bilevel optimization model to two case studies, namely, e-hailing driver repositioning under service charge and multiclass taxi driver repositioning under NYC congestion pricing. In the first case study, the model is validated by the agreement between the derived optimal control from BO and that from an analytical solution. With a simple piecewise linear service charge, the objective of the e-hailing platform can be increased by 4.0%. In the second case study, an optimal toll charge of $5.1 is solved using BO, which improves the objective of city planners by 7.9%, compared to that without any toll charge. Under this optimal toll charge, the number of taxis in the NYC central business district is decreased, indicating a better traffic condition, without substantially increasing the crowdedness of the subway system.

The deep reinforcement learning method for human-robot cooperation (HRC) is promising for its high performance when robots are learning complex tasks. However, the applicability of such an approach in a real-world context is limited due to long training time, additional training difficulty caused by inconsistent human performance and the inherent instability of policy exploration. With this approach, the robot has two dynamics to learn: how to accomplish the given physical task and how to cooperate with the human partner. Furthermore, the dynamics of the task and human partner are usually coupled, which means the observable outcomes and behaviors are coupled. It is hard for the robot to efficiently learn from coupled observations. In this paper, we hypothesize that the robot needs to learn the task separately from learning the behavior of the human partner to improve learning efficiency and outcomes. This leads to a fundamental question: Should the robot learn the task first or learn the human behavior first (Fig. 1)? We develop a novel hierarchical rewards mechanism with a task decomposition method that enables the robot to efficiently learn a complex hierarchical dynamic task and human behavior for better HRC. The algorithm is validated in a hierarchical control task in a simulated environment with human subject experiments, and we are able to answer the question by analyzing the collected experiment results.