In Cooperative Multi-Agent Reinforcement Learning (MARL) and under the setting of Centralized Training with Decentralized Execution (CTDE), agents observe and interact with their environment locally and independently. With local observation and random sampling, the randomness in rewards and observations leads to randomness in long-term returns. Existing methods such as Value Decomposition Network (VDN) and QMIX estimate the value of long-term returns as a scalar that does not contain the information of randomness. Our proposed model QR-MIX introduces quantile regression, modeling joint state-action values as a distribution, combining QMIX with Implicit Quantile Network (IQN). However, the monotonicity in QMIX limits the expression of joint state-action value distribution and may lead to incorrect estimation results in non-monotonic cases. Therefore, we proposed a flexible loss function to approximate the monotonicity found in QMIX. Our model is not only more tolerant of the randomness of returns, but also more tolerant of the randomness of monotonic constraints. The experimental results demonstrate that QR-MIX outperforms the previous state-of-the-art method QMIX in the StarCraft Multi-Agent Challenge (SMAC) environment.

Deep reinforcement learning (DRL) is an emerging methodology that is transforming the way many complicated transportation decision-making problems are tackled. Researchers have been increasingly turning to this powerful learning-based methodology to solve challenging problems across transportation fields. While many promising applications have been reported in the literature, there remains a lack of comprehensive synthesis of the many DRL algorithms and their uses and adaptations. The objective of this paper is to fill this gap by conducting a comprehensive, synthesized review of DRL applications in transportation. We start by offering an overview of the DRL mathematical background, popular and promising DRL algorithms, and some highly effective DRL extensions. Building on this overview, a systematic investigation of about 150 DRL studies that have appeared in the transportation literature, divided into seven different categories, is performed. Building on this review, we continue to examine the applicability, strengths, shortcomings, and common and application-specific issues of DRL techniques with regard to their applications in transportation. In the end, we recommend directions for future research and present available resources for actually implementing DRL.

Emergent behavior is a key feature defining a system under study as a complex system. Simulation has been recognized as the only way to deal with the study of the emergency of properties (at a macroscopic level) among groups of system components (at a microscopic level), for the manifestations of emergent structures cannot be deduced from analysing components in isolation. A systems-oriented generalisation must consider the presence of feedback loops (micro components react to macro properties), interaction among components of different classes (modular composition) and layered interaction of subsystems operating at different spatio-temporal scales (hierarchical organisation). In this work we introduce Emergent Behavior-DEVS (EB-DEVS) a Modeling and Simulation (M&S) formalism that permits reasoning about complex systems where emergent behavior is placed at the forefront of the analysis activity. EB-DEVS builds on the DEVS formalism, adding upward/downward communication channels to well-established capabilities for modular and hierarchical M&S of heterogeneous multi-formalism systems. EB-DEVS takes a minimalist stance on expressiveness, introducing a small set of extensions on Classic DEVS that can cope with emergent behavior, and making both formalisms interoperable (the modeler decides which subsystems deserve to be expressed via micro-macro dynamics). We present three case studies: flocks of birds with learning, population epidemics with vaccination and sub-cellular dynamics with homeostasis, through which we showcase how EB-DEVS performs by placing emergent properties at the center of the M&S process.

Connected Autonomous Vehicle (CAV) Network can be defined as a collection of CAVs operating at different locations on a multilane corridor, which provides a platform to facilitate the dissemination of operational information as well as control instructions. Cooperation is crucial in CAV operating systems since it can greatly enhance operation in terms of safety and mobility, and high-level cooperation between CAVs can be expected by jointly plan and control within CAV network. However, due to the highly dynamic and combinatory nature such as dynamic number of agents (CAVs) and exponentially growing joint action space in a multiagent driving task, achieving cooperative control is NP hard and cannot be governed by any simple rule-based methods. In addition, existing literature contains abundant information on autonomous driving's sensing technology and control logic but relatively little guidance on how to fuse the information acquired from collaborative sensing and build decision processor on top of fused information. In this paper, a novel Deep Reinforcement Learning (DRL) based approach combining Graphic Convolution Neural Network (GCN) and Deep Q Network (DQN), namely Graphic Convolution Q network (GCQ) is proposed as the information fusion module and decision processor. The proposed model can aggregate the information acquired from collaborative sensing and output safe and cooperative lane changing decisions for multiple CAVs so that individual intention can be satisfied even under a highly dynamic and partially observed mixed traffic. The proposed algorithm can be deployed on centralized control infrastructures such as road-side units (RSU) or cloud platforms to improve the CAV operation.

Modeling the complex interactions of systems of particles or agents is a fundamental scientific and mathematical problem that is studied in diverse fields, ranging from physics and biology, to economics and machine learning. In this work, we describe a very general second-order, heterogeneous, multivariable, interacting agent model, with an environment, that encompasses a wide variety of known systems. We describe an inference framework that uses nonparametric regression and approximation theory based techniques to efficiently derive estimators of the interaction kernels which drive these dynamical systems. We develop a complete learning theory which establishes strong consistency and optimal nonparametric min-max rates of convergence for the estimators, as well as provably accurate predicted trajectories. The estimators exploit the structure of the equations in order to overcome the curse of dimensionality and we describe a fundamental coercivity condition on the inverse problem which ensures that the kernels can be learned and relates to the minimal singular value of the learning matrix. The numerical algorithm presented to build the estimators is parallelizable, performs well on high-dimensional problems, and is demonstrated on complex dynamical systems.

This paper focuses on cooperative value-based multi-agent reinforcement learning (MARL) in the paradigm of centralized training with decentralized execution (CTDE). Current state-of-the-art value-based MARL methods leverage CTDE to learn a centralized joint-action value function as a monotonic mixing of each agent's utility function, which enables easy decentralization. However, this monotonic restriction leads to inefficient exploration in tasks with nonmonotonic returns due to suboptimal approximations of the values of joint actions. To address this, we present a novel MARL approach called Universal Value Exploration (UneVEn), which uses universal successor features (USFs) to learn policies of tasks related to the target task, but with simpler reward functions in a sample efficient manner. UneVEn uses novel action-selection schemes between randomly sampled related tasks during exploration, which enables the monotonic joint-action value function of the target task to place more importance on useful joint actions. Empirical results on a challenging cooperative predator-prey task requiring significant coordination amongst agents show that UneVEn significantly outperforms state-of-the-art baselines.

The objective of meta-learning is to exploit the knowledge obtained from observed tasks to improve adaptation to unseen tasks. As such, meta-learners are able to generalize better when they are trained with a larger number of observed tasks and with a larger amount of data per task. Given the amount of resources that are needed, it is generally difficult to expect the tasks, their respective data, and the necessary computational capacity to be available at a single central location. It is more natural to encounter situations where these resources are spread across several agents connected by some graph topology. The formalism of meta-learning is actually well-suited to this decentralized setting, where the learner would be able to benefit from information and computational power spread across the agents. Motivated by this observation, in this work, we propose a cooperative fully-decentralized multi-agent meta-learning algorithm, referred to as Diffusion-based MAML or Dif-MAML. Decentralized optimization algorithms are superior to centralized implementations in terms of scalability, avoidance of communication bottlenecks, and privacy guarantees. The work provides a detailed theoretical analysis to show that the proposed strategy allows a collection of agents to attain agreement at a linear rate and to converge to a stationary point of the aggregate MAML objective even in non-convex environments. Simulation results illustrate the theoretical findings and the superior performance relative to the traditional non-cooperative setting.

Societal rules, as exemplified by norms, aim to provide a degree of behavioural stability to multi-agent societies. Norms regulate a society using the deontic concepts of permissions, obligations and prohibitions to specify what can, must and must not occur in a society. Many implementations of normative systems assume various combinations of the following assumptions: that the set of norms is static and defined at design time; that agents joining a society are instantly informed of the complete set of norms; that the set of agents within a society does not change; and that all agents are aware of the existing norms. When any one of these assumptions is dropped, agents need a mechanism to identify the set of norms currently present within a society, or risk unwittingly violating the norms. In this paper, we develop a norm identification mechanism that uses a combination of parsing-based plan recognition and Hierarchical Task Network (HTN) planning mechanisms, which operates by analysing the actions performed by other agents. While our basic mechanism cannot learn in situations where norm violations take place, we describe an extension which is able to operate in the presence of violations.

Multi-Agent Reinforcement Learning (MARL) has demonstrated significant success in training decentralised policies in a centralised manner by making use of value factorization methods. However, addressing surprise across spurious states and approximation bias remain open problems for multi-agent settings. We introduce the Energy-based MIXer (EMIX), an algorithm which minimizes surprise utilizing the energy across agents. Our contributions are threefold; (1) EMIX introduces a novel surprise minimization technique across multiple agents in the case of multi-agent partially-observable settings. (2) EMIX highlights the first practical use of energy functions in MARL (to our knowledge) with theoretical guarantees and experiment validations of the energy operator. Lastly, (3) EMIX presents a novel technique for addressing overestimation bias across agents in MARL. When evaluated on a range of challenging StarCraft II micromanagement scenarios, EMIX demonstrates consistent state-of-the-art performance for multi-agent surprise minimization. Moreover, our ablation study highlights the necessity of the energy-based scheme and the need for elimination of overestimation bias in MARL. Our implementation of EMIX and videos of agents are available at https://karush17.github.io/emix-web/.

QTRAN is a multi-agent reinforcement learning (MARL) algorithm capable of learning the largest class of joint-action value functions up to date. However, despite its strong theoretical guarantee, it has shown poor empirical performance in complex environments, such as Starcraft Multi-Agent Challenge (SMAC). In this paper, we identify the performance bottleneck of QTRAN and propose a substantially improved version, coined QTRAN++. Our gains come from (i) stabilizing the training objective of QTRAN, (ii) removing the strict role separation between the action-value estimators of QTRAN, and (iii) introducing a multi-head mixing network for value transformation. Through extensive evaluation, we confirm that our diagnosis is correct, and QTRAN++ successfully bridges the gap between empirical performance and theoretical guarantee. In particular, QTRAN++ newly achieves state-of-the-art performance in the SMAC environment. The code will be released.