Reinforcement learning (RL) is an increasingly popular way to model sequential decision-making problems in artificial intelligence. RL agents learn through trial and error, repeatedly interacting with the world to learn a policy that maximizes a reward signal. RL agents have recently achieved remarkable results when used in conjunction with deep neural networks. Chief among these so-called deep-RL results is the 2015 paper that introduced the Deep Q Network (DQN) agent, which surpassed human-level performance on a large set of Atari games. A core component of DQN is an optimizer that adapts the parameters of the neural network to minimize the DQN objective.

The unit commitment (UC) problem, which determines operating schedules of generation units to meet demand, is a fundamental task in power systems operation. Existing UC methods using mixed-integer programming are not well-suited to highly stochastic systems. Approaches which more rigorously account for uncertainty could yield large reductions in operating costs by reducing spinning reserve requirements; operating power stations at higher efficiencies; and integrating greater volumes of variable renewables. A promising approach to solving the UC problem is reinforcement learning (RL), a methodology for optimal decision-making which has been used to conquer long-standing grand challenges in artificial intelligence. This thesis explores the application of RL to the UC problem and addresses challenges including robustness under uncertainty; generalisability across multiple problem instances; and scaling to larger power systems than previously studied. To tackle these issues, we develop guided tree search, a novel methodology combining model-free RL and model-based planning. The UC problem is formalised as a Markov decision process and we develop an open-source environment based on real data from Great Britain's power system to train RL agents. In problems of up to 100 generators, guided tree search is shown to be competitive with deterministic UC methods, reducing operating costs by up to 1.4\%. An advantage of RL is that the framework can be easily extended to incorporate considerations important to power systems operators such as robustness to generator failure, wind curtailment or carbon prices. When generator outages are considered, guided tree search saves over 2\% in operating costs as compared with methods using conventional $N-x$ reserve criteria.

Safety comes first in many real-world applications involving autonomous agents. Despite a large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there is still a lack of high-quality evaluation of those algorithms that adheres to safety constraints at each decision step under complex and unknown dynamics. In this paper, we revisit prior work in this scope from the perspective of state-wise safe RL and categorize them as projection-based, recovery-based, and optimization-based approaches, respectively. Furthermore, we propose Unrolling Safety Layer (USL), a joint method that combines safety optimization and safety projection. This novel technique explicitly enforces hard constraints via the deep unrolling architecture and enjoys structural advantages in navigating the trade-off between reward improvement and constraint satisfaction. To facilitate further research in this area, we reproduce related algorithms in a unified pipeline and incorporate them into SafeRL-Kit, a toolkit that provides off-the-shelf interfaces and evaluation utilities for safety-critical tasks. We then perform a comparative study of the involved algorithms on six benchmarks ranging from robotic control to autonomous driving. The empirical results provide an insight into their applicability and robustness in learning zero-cost-return policies without task-dependent handcrafting. The project page is available at https://sites.google.com/view/saferlkit.

Proximal Policy Optimization (PPO) is a highly popular policy-based deep reinforcement learning (DRL) approach. However, we observe that the homogeneous exploration process in PPO could cause an unexpected stability issue in the training phase. To address this issue, we propose PPO-UE, a PPO variant equipped with self-adaptive uncertainty-aware explorations (UEs) based on a ratio uncertainty level. The proposed PPO-UE is designed to improve convergence speed and performance with an optimized ratio uncertainty level. Through extensive sensitivity analysis by varying the ratio uncertainty level, our proposed PPO-UE considerably outperforms the baseline PPO in Roboschool continuous control tasks.

We study time-inhomogeneous episodic reinforcement learning (RL) under general function approximation and sparse rewards. We design a new algorithm, Variance-weighted Optimistic $Q$-Learning (VO$Q$L), based on $Q$-learning and bound its regret assuming completeness and bounded Eluder dimension for the regression function class. As a special case, VO$Q$L achieves $\tilde{O}(d\sqrt{HT}+d^6H^{5})$ regret over $T$ episodes for a horizon $H$ MDP under ($d$-dimensional) linear function approximation, which is asymptotically optimal. Our algorithm incorporates weighted regression-based upper and lower bounds on the optimal value function to obtain this improved regret. The algorithm is computationally efficient given a regression oracle over the function class, making this the first computationally tractable and statistically optimal approach for linear MDPs.

The performance of decision policies and prediction models often deteriorates when applied to environments different from the ones seen during training. To ensure reliable operation, we propose and analyze the stability of a system under distribution shift, which is defined as the smallest change in the underlying environment that causes the system's performance to deteriorate beyond a permissible threshold. In contrast to standard tail risk measures and distributionally robust losses that require the specification of a plausible magnitude of distribution shift, the stability measure is defined in terms of a more intuitive quantity: the level of acceptable performance degradation. We develop a minimax optimal estimator of stability and analyze its convergence rate, which exhibits a fundamental phase shift behavior. Our characterization of the minimax convergence rate shows that evaluating stability against large performance degradation incurs a statistical cost. Empirically, we demonstrate the practical utility of our stability framework by using it to compare system designs on problems where robustness to distribution shift is critical.

Reinforcement learning allows machines to learn from their own experience. Nowadays, it is used in safety-critical applications, such as autonomous driving, despite being vulnerable to attacks carefully crafted to either prevent that the reinforcement learning algorithm learns an effective and reliable policy, or to induce the trained agent to make a wrong decision. The literature about the security of reinforcement learning is rapidly growing, and some surveys have been proposed to shed light on this field. However, their categorizations are insufficient for choosing an appropriate defense given the kind of system at hand. In our survey, we do not only overcome this limitation by considering a different perspective, but we also discuss the applicability of state-of-the-art attacks and defenses when reinforcement learning algorithms are used in the context of autonomous driving.

Exploratory data analytics (EDA) is a sequential decision making process where analysts choose subsequent queries that might lead to some interesting insights based on the previous queries and corresponding results. Data processing systems often execute the queries on samples to produce results with low latency. Different downsampling strategy preserves different statistics of the data and have different magnitude of latency reductions. The optimum choice of sampling strategy often depends on the particular context of the analysis flow and the hidden intent of the analyst. In this paper, we are the first to consider the impact of sampling in interactive data exploration settings as they introduce approximation errors. We propose a Deep Reinforcement Learning (DRL) based framework which can optimize the sample selection in order to keep the analysis and insight generation flow intact. Evaluations with 3 real datasets show that our technique can preserve the original insight generation flow while improving the interaction latency, compared to baseline methods.

Online ride-hailing services have become a prevalent transportation system across the world. In this paper, we study a challenging problem of how to direct vacant taxis around a city such that supplies and demands can be balanced in online ride-hailing services. We design a new reward scheme that considers multiple performance metrics of online ride-hailing services. We also propose a novel deep reinforcement learning method named Deep-Q-Network with Action Mask (AM-DQN) masking off unnecessary actions in various locations such that agents can learn much faster and more efficiently. We conduct extensive experiments using a city-scale dataset from Chicago. Several popular heuristic and learning methods are also implemented as baselines for comparison. The results of the experiments show that the AM-DQN attains the best performances of all methods with respect to average failure rate, average waiting time for customers, and average idle search time for vacant taxis.

Reinforcement learning (RL) is one of the most vibrant research frontiers in machine learning and has been recently applied to solve a number of challenging problems. In this paper, we primarily focus on off-policy evaluation (OPE), one of the most fundamental topics in RL. In recent years, a number of OPE methods have been developed in the statistics and computer science literature. We provide a discussion on the efficiency bound of OPE, some of the existing state-of-the-art OPE methods, their statistical properties and some other related research directions that are currently actively explored.