We introduce DeepNash, an autonomous agent capable of learning to play the imperfect information game Stratego from scratch, up to a human expert level. Stratego is one of the few iconic board games that Artificial Intelligence (AI) has not yet mastered. This popular game has an enormous game tree on the order of $10^{535}$ nodes, i.e., $10^{175}$ times larger than that of Go. It has the additional complexity of requiring decision-making under imperfect information, similar to Texas hold'em poker, which has a significantly smaller game tree (on the order of $10^{164}$ nodes). Decisions in Stratego are made over a large number of discrete actions with no obvious link between action and outcome. Episodes are long, with often hundreds of moves before a player wins, and situations in Stratego can not easily be broken down into manageably-sized sub-problems as in poker. For these reasons, Stratego has been a grand challenge for the field of AI for decades, and existing AI methods barely reach an amateur level of play. DeepNash uses a game-theoretic, model-free deep reinforcement learning method, without search, that learns to master Stratego via self-play. The Regularised Nash Dynamics (R-NaD) algorithm, a key component of DeepNash, converges to an approximate Nash equilibrium, instead of 'cycling' around it, by directly modifying the underlying multi-agent learning dynamics. DeepNash beats existing state-of-the-art AI methods in Stratego and achieved a yearly (2022) and all-time top-3 rank on the Gravon games platform, competing with human expert players.

Platooning and coordination are two implementation strategies that are frequently proposed for traffic control of connected and autonomous vehicles (CAVs) at signal-free intersections instead of using conventional traffic signals. However, few studies have attempted to integrate both strategies to better facilitate the CAV control at signal-free intersections. To this end, this study proposes a hierarchical control model, named COOR-PLT, to coordinate adaptive CAV platoons at a signal-free intersection based on deep reinforcement learning (DRL). COOR-PLT has a two-layer framework. The first layer uses a centralized control strategy to form adaptive platoons. The optimal size of each platoon is determined by considering multiple objectives (i.e., efficiency, fairness and energy saving). The second layer employs a decentralized control strategy to coordinate multiple platoons passing through the intersection. Each platoon is labeled with coordinated status or independent status, upon which its passing priority is determined. As an efficient DRL algorithm, Deep Q-network (DQN) is adopted to determine platoon sizes and passing priorities respectively in the two layers. The model is validated and examined on the simulator Simulation of Urban Mobility (SUMO). The simulation results demonstrate that the model is able to: (1) achieve satisfactory convergence performances; (2) adaptively determine platoon size in response to varying traffic conditions; and (3) completely avoid deadlocks at the intersection. By comparison with other control methods, the model manifests its superiority of adopting adaptive platooning and DRL-based coordination strategies. Also, the model outperforms several state-of-the-art methods on reducing travel time and fuel consumption in different traffic conditions.

As machine learning-based models continue to be developed for healthcare applications, greater effort is needed in ensuring that these technologies do not reflect or exacerbate any unwanted or discriminatory biases that may be present in the data. In this study, we introduce a reinforcement learning framework capable of mitigating biases that may have been acquired during data collection. In particular, we evaluated our model for the task of rapidly predicting COVID-19 for patients presenting to hospital emergency departments, and aimed to mitigate any site-specific (hospital) and ethnicity-based biases present in the data. Using a specialized reward function and training procedure, we show that our method achieves clinically-effective screening performances, while significantly improving outcome fairness compared to current benchmarks and state-of-the-art machine learning methods. We performed external validation across three independent hospitals, and additionally tested our method on a patient ICU discharge status task, demonstrating model generalizability.

Online influence maximization aims to maximize the influence spread of a content in a social network with unknown network model by selecting a few seed nodes. Recent studies followed a non-adaptive setting, where the seed nodes are selected before the start of the diffusion process and network parameters are updated when the diffusion stops. We consider an adaptive version of content-dependent online influence maximization problem where the seed nodes are sequentially activated based on real-time feedback. In this paper, we formulate the problem as an infinite-horizon discounted MDP under a linear diffusion process and present a model-based reinforcement learning solution. Our algorithm maintains a network model estimate and selects seed users adaptively, exploring the social network while improving the optimal policy optimistically. We establish $\widetilde O(\sqrt{T})$ regret bound for our algorithm. Empirical evaluations on synthetic network demonstrate the efficiency of our algorithm.

Emergency vehicles (EMVs) play a crucial role in responding to time-critical calls such as medical emergencies and fire outbreaks in urban areas. Existing methods for EMV dispatch typically optimize routes based on historical traffic-flow data and design traffic signal pre-emption accordingly; however, we still lack a systematic methodology to address the coupling between EMV routing and traffic signal control. In this paper, we propose EMVLight, a decentralized reinforcement learning (RL) framework for joint dynamic EMV routing and traffic signal pre-emption. We adopt the multi-agent advantage actor-critic method with policy sharing and spatial discounted factor. This framework addresses the coupling between EMV navigation and traffic signal control via an innovative design of multi-class RL agents and a novel pressure-based reward function. The proposed methodology enables EMVLight to learn network-level cooperative traffic signal phasing strategies that not only reduce EMV travel time but also shortens the travel time of non-EMVs. Simulation-based experiments indicate that EMVLight enables up to a $42.6\%$ reduction in EMV travel time as well as an $23.5\%$ shorter average travel time compared with existing approaches.

This book provides a collection of recent research works addressing theoretical issues on improving the learning process and the generalization of GANs as well as state-of-the-art applications of GANs to various domains of real life. Generative adversarial networks (GANs), as the main method of adversarial learning, achieve great success and popularity by exploiting a minimax learning concept, in which two networks compete with each other during the learning process. Their key capability is to generate new data and replicate available data distributions, which are needed in many practical applications, particularly in computer vision and signal processing. The book is intended for academics, practitioners, and research students in artificial intelligence looking to stay up to date with the latest advancements on GANs' theoretical developments and their applications.

Engineers at Rice University have developed a method that allows humans to help robots "see" their environments and carry out tasks. The strategy called Bayesian Learning IN the Dark -- BLIND, for short -- is a novel solution to the long-standing problem of motion planning for robots that work in environments where not everything is clearly visible all the time. The peer-reviewed study led by computer scientists Lydia Kavraki and Vaibhav Unhelkar and co-lead authors Carlos Quintero-Peña and Constantinos Chamzas of Rice's George R. Brown School of Engineering was presented at the Institute of Electrical and Electronics Engineers' International Conference on Robotics and Automation in late May. The algorithm developed primarily by Quintero-Peña and Chamzas, both graduate students working with Kavraki, keeps a human in the loop to "augment robot perception and, importantly, prevent the execution of unsafe motion," according to the study. To do so, they combined Bayesian inverse reinforcement learning (by which a system learns from continually updated information and experience) with established motion planning techniques to assist robots that have "high degrees of freedom" -- that is, a lot of moving parts.

Precision agriculture is rapidly attracting research to efficiently introduce automation and robotics solutions to support agricultural activities. Robotic navigation in vineyards and orchards offers competitive advantages in autonomously monitoring and easily accessing crops for harvesting, spraying and performing time-consuming necessary tasks. Nowadays, autonomous navigation algorithms exploit expensive sensors which also require heavy computational cost for data processing. Nonetheless, vineyard rows represent a challenging outdoor scenario where GPS and Visual Odometry techniques often struggle to provide reliable positioning information. In this work, we combine Edge AI with Deep Reinforcement Learning to propose a cutting-edge lightweight solution to tackle the problem of autonomous vineyard navigation without exploiting precise localization data and overcoming task-tailored algorithms with a flexible learning-based approach. We train an end-to-end sensorimotor agent which directly maps noisy depth images and position-agnostic robot state information to velocity commands and guides the robot to the end of a row, continuously adjusting its heading for a collision-free central trajectory. Our extensive experimentation in realistic simulated vineyards demonstrates the effectiveness of our solution and the generalization capabilities of our agent.

Reinforcement learning (RL) is a machine learning (ML) paradigm that is capable of optimizing sequential decisions. RL is interesting because it mimics how we, as humans, learn. We are instinctively capable of learning strategies that help us master complex tasks like riding a bike or taking a mathematics exam. RL attempts to copy this process by interacting with the environment to learn strategies. Recently, businesses have been applying ML algorithms to make one-shot decisions. These are trained upon data to make the best decision at the time.

Parameter adaptation, that is the capability to automatically adjust an algorithm's hyperparameters depending on the problem being faced, is one of the main trends in evolutionary computation applied to numerical optimization. While several handcrafted adaptation policies have been proposed over the years to address this problem, only few attempts have been done so far at apply machine learning to learn such policies. Here, we introduce a general-purpose framework for performing parameter adaptation in continuous-domain metaheuristics based on state-of-the-art reinforcement learning algorithms. We demonstrate the applicability of this framework on two algorithms, namely Covariance Matrix Adaptation Evolution Strategies (CMA-ES) and Differential Evolution (DE), for which we learn, respectively, adaptation policies for the step-size (for CMA-ES), and the scale factor and crossover rate (for DE). We train these policies on a set of 46 benchmark functions at different dimensionalities, with various inputs to the policies, in two settings: one policy per function, and one global policy for all functions.