Reinforcement learning (RL) is attracting increasing interests in autonomous driving due to its potential to solve complex classification and control problems. However, existing RL algorithms are rarely applied to real vehicles for two predominant problems: behaviours are unexplainable, and they cannot guarantee safety under new scenarios. This paper presents a safe RL algorithm, called Parallel Constrained Policy Optimization (PCPO), for two autonomous driving tasks. PCPO extends today's common actor-critic architecture to a three-component learning framework, in which three neural networks are used to approximate the policy function, value function and a newly added risk function, respectively. Meanwhile, a trust region constraint is added to allow large update steps without breaking the monotonic improvement condition. To ensure the feasibility of safety constrained problems, synchronized parallel learners are employed to explore different state spaces, which accelerates learning and policy-update. The simulations of two scenarios for autonomous vehicles confirm we can ensure safety while achieving fast learning.

Emergency vehicle (EV) service is a key function of cities and is exceedingly challenging due to urban traffic congestion. A key contributor to EV service delay is the lack of communication and cooperation between vehicles blocking EVs. In this paper, we study the improvement of EV service using vehicle-to-vehicle connectivity. We consider the establishment of dynamic queue jumper lanes (DQJLs) based on real-time coordination of connected vehicles. We develop a novel stochastic dynamic programming formulation for the DQJL problem, which explicitly account for the uncertainty of drivers' reaction to approaching EVs. We propose a deep neural network-based approximate dynamic programming (ADP) algorithm that efficiently computes the optimal coordination instructions. We also validate our approach on a micro-simulation testbed using Simulation On Urban Mobility (SUMO).

Regular Decision Processes (RDPs) are a recently introduced model that extends MDPs with non-Markovian dynamics and rewards. The non-Markovian behavior is restricted to depend on regular properties of the history. These can be specified using regular expressions or formulas in linear dynamic logic over finite traces. Fully specified RDPs can be solved by compiling them into an appropriate MDP. Learning RDPs from data is a challenging problem that has yet to be addressed, on which we focus in this paper. Our approach rests on a new representation for RDPs using Mealy Machines that emit a distribution and an expected reward for each state-action pair. Building on this representation, we combine automata learning techniques with history clustering to learn such a Mealy machine and solve it by adapting MCTS to it. We empirically evaluate this approach, demonstrating its feasibility.

Tuning hyper-parameters for evolutionary algorithms is an important issue in computational intelligence. Performance of an evolutionary algorithm depends not only on its operation strategy design, but also on its hyper-parameters. Hyper-parameters can be categorized in two dimensions as structural/numerical and time-invariant/time-variant. Particularly, structural hyper-parameters in existing studies are usually tuned in advance for time-invariant parameters, or with hand-crafted scheduling for time-invariant parameters. In this paper, we make the first attempt to model the tuning of structural hyper-parameters as a reinforcement learning problem, and present to tune the structural hyper-parameter which controls computational resource allocation in the CEC 2018 winner algorithm by Q-learning. Experimental results show favorably against the winner algorithm on the CEC 2018 test functions.

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.