In this paper, we study the problem of learning to satisfy temporal logic specifications with a group of agents in an unknown environment, which may exhibit probabilistic behaviour. From a learning perspective these specifications provide a rich formal language with which to capture tasks or objectives, while from a logic and automated verification perspective the introduction of learning capabilities allows for practical applications in large, stochastic, unknown environments. The existing work in this area is, however, limited. Of the frameworks that consider full linear temporal logic or have correctness guarantees, all methods thus far consider only the case of a single temporal logic specification and a single agent. In order to overcome this limitation, we develop the first multi-agent reinforcement learning technique for temporal logic specifications, which is also novel in its ability to handle multiple specifications. We provide correctness and convergence guarantees for our main algorithm - ALMANAC (Automaton/Logic Multi-Agent Natural Actor-Critic) - even when using function approximation. Alongside our theoretical results, we further demonstrate the applicability of our technique via a set of preliminary experiments.

Nature-inspired algorithms are commonly used for solving the various optimization problems. In past few decades, various researchers have proposed a large number of nature-inspired algorithms. Some of these algorithms have proved to be very efficient as compared to other classical optimization methods. A young researcher attempting to undertake or solve a problem using nature-inspired algorithms is bogged down by a plethora of proposals that exist today. Not every algorithm is suited for all kinds of problem. Some score over others. In this paper, an attempt has been made to summarize various leading research proposals that shall pave way for any new entrant to easily understand the journey so far. Here, we classify the nature-inspired algorithms as natural evolution based, swarm intelligence based, biological based, science based and others. In this survey, widely acknowledged nature-inspired algorithms namely- ACO, ABC, EAM, FA, FPA, GA, GSA, JAYA, PSO, SFLA, TLBO and WCA, have been studied. The purpose of this review is to present an exhaustive analysis of various nature-inspired algorithms based on its source of inspiration, basic operators, control parameters, features, variants and area of application where these algorithms have been successfully applied. It shall also assist in identifying and short listing the methodologies that are best suited for the problem.

Centralized Training for Decentralized Execution, where agents are trained offline using centralized information but execute in a decentralized manner online, has gained popularity in the multi-agent reinforcement learning community. In particular, actor-critic methods with a centralized critic and decentralized actors are a common instance of this idea. However, the implications of using a centralized critic in this context are not fully discussed and understood even though it is the standard choice of many algorithms. We therefore formally analyze centralized and decentralized critic approaches, providing a deeper understanding of the implications of critic choice. Because our theory makes unrealistic assumptions, we also empirically compare the centralized and decentralized critic methods over a wide set of environments to validate our theories and to provide practical advice. We show that there exist misconceptions regarding centralized critics in the current literature and show that the centralized critic design is not strictly beneficial, but rather both centralized and decentralized critics have different pros and cons that should be taken into account by algorithm designers.

Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task. The limitation is due to the restricted model architecture related to fixed input and output dimensions. This hinders the experience accumulation and transfer of the learned agent over tasks with diverse levels of difficulty (e.g. 3 vs 3 or 5 vs 6 multi-agent games). In this paper, we make the first attempt to explore a universal multi-agent reinforcement learning pipeline, designing one single architecture to fit tasks with the requirement of different observation and action configurations. Unlike previous RNN-based models, we utilize a transformer-based model to generate a flexible policy by decoupling the policy distribution from the intertwined input observation with an importance weight measured by the merits of the self-attention mechanism. Compared to a standard transformer block, the proposed model, named as Universal Policy Decoupling Transformer (UPDeT), further relaxes the action restriction and makes the multi-agent task's decision process more explainable. UPDeT is general enough to be plugged into any multi-agent reinforcement learning pipeline and equip them with strong generalization abilities that enables the handling of multiple tasks at a time. Extensive experiments on large-scale SMAC multi-agent competitive games demonstrate that the proposed UPDeT-based multi-agent reinforcement learning achieves significant results relative to state-of-the-art approaches, demonstrating advantageous transfer capability in terms of both performance and training speed (10 times faster).

Recently, distributed controller architectures have been quickly gaining popularity in Software-Defined Networking (SDN). However, the use of distributed controllers introduces a new and important Request Dispatching (RD) problem with the goal for every SDN switch to properly dispatch their requests among all controllers so as to optimize network performance. This goal can be fulfilled by designing an RD policy to guide distribution of requests at each switch. In this paper, we propose a Multi-Agent Deep Reinforcement Learning (MA-DRL) approach to automatically design RD policies with high adaptability and performance. This is achieved through a new problem formulation in the form of a Multi-Agent Markov Decision Process (MA-MDP), a new adaptive RD policy design and a new MA-DRL algorithm called MA-PPO. Extensive simulation studies show that our MA-DRL technique can effectively train RD policies to significantly outperform man-made policies, model-based policies, as well as RD policies learned via single-agent DRL algorithms.

While the complexity of computing Bayes-Nash equilibria Applications of combinatorial auctions (CA) as market mechanisms (BNE) is not well understood, Cai and Papadimitriou [14] show that are prevalent in practice, yet their Bayesian Nash equilibria (BNE) BNE computation for a specific combinatorial auction is already (at remain poorly understood. Analytical solutions are known only for least) PP-hard. Furthermore, finding an -approximation to a BNE is a few cases where the problem can be reformulated as a tractable still NP-hard. Explicit solutions exist for very few specific environments, partial differential equation (PDE). In the general case, finding BNE but in general, we neither know whether a BNE exists nor is known to be computationally hard. Previous work on numerical do we have a solution theory. Combinatorial auctions have become computation of BNE in auctions has relied either on solving such a pivotal research problem in algorithmic game theory [29] and PDEs explicitly, calculating pointwise best-responses in strategy they are widely used in the field [8, 15]. Thus, understanding their space, or iteratively solving restricted subgames. In this study, we equilibria is paramount, and access to scalable numerical methods present a generic yet scalable alternative multi-agent equilibrium for computing or approximating BNE can have a significant impact.

With large-scale integration of renewable generation and ubiquitous distributed energy resources (DERs), modern power systems confront a series of new challenges in operation and control, such as growing complexity, increasing uncertainty, and aggravating volatility. While the upside is that more and more data are available owing to the widely-deployed smart meters, smart sensors, and upgraded communication networks. As a result, data-driven control techniques, especially reinforcement learning (RL), have attracted surging attention in recent years. In this paper, we focus on RL and aim to provide a tutorial on various RL techniques and how they can be applied to the decision-making and control in power systems. In particular, we select three key applications, including frequency regulation, voltage control, and energy management, for illustration, and present the typical ways to model and tackle them with RL methods. We conclude by emphasizing two critical issues in the application of RL, i.e., safety and scalability. Several potential future directions are discussed as well.

In recent years, multi-agent deep reinforcement learning has been successfully applied to various complicated scenarios such as computer games and robot swarms. We thoroughly study and compare the state-of-the-art cooperative multi-agent deep reinforcement learning algorithms. Specifically, we investigate the consequences of the "hyperparameter tricks" of QMIX and its improved variants. Our results show that: (1) The significant performance improvements of these variant algorithms come from hyperparameter-level optimizations in their open-source codes (2) After modest tuning and with no changes to the network architecture, QMIX can attain extraordinarily high win rates in all hard and super hard scenarios of StarCraft Multi-Agent Challenge (SMAC) and achieve state-of-the-art (SOTA). In this work, we proposed a reliable QMIX benchmark, which will be of great benefit to subsequent research. Besides, we proposed a hypothesis to explain the excellent performance of QMIX.

With Artificial Intelligence on the rise, human interaction with autonomous agents becomes more frequent. Effective human-agent collaboration requires that the human understands the agent's behavior, as failing to do so may lead to reduced productiveness, misuse, frustration and even danger. Agent strategy summarization methods are used to describe the strategy of an agent to its destined user through demonstration. The summary's purpose is to maximize the user's understanding of the agent's aptitude by showcasing its behaviour in a set of world states, chosen by some importance criteria. While shown to be useful, we show that these methods are limited in supporting the task of comparing agent behavior, as they independently generate a summary for each agent. In this paper, we propose a novel method for generating contrastive summaries that highlight the differences between agent's policies by identifying and ranking states in which the agents disagree on the best course of action. We conduct a user study in which participants face an agent selection task. Our results show that the novel disagreement-based summaries lead to improved user performance compared to summaries generated using HIGHLIGHTS, a previous strategy summarization algorithm.

Balancing safety and efficiency when planning in dense traffic is challenging. Interactive behavior planners incorporate prediction uncertainty and interactivity inherent to these traffic situations. Yet, their use of single-objective optimality impedes interpretability of the resulting safety goal. Safety envelopes which restrict the allowed planning region yield interpretable safety under the presence of behavior uncertainty, yet, they sacrifice efficiency in dense traffic due to conservative driving. Studies show that humans balance safety and efficiency in dense traffic by accepting a probabilistic risk of violating the safety envelope. In this work, we adopt this safety objective for interactive planning. Specifically, we formalize this safety objective, present the Risk-Constrained Robust Stochastic Bayesian Game modeling interactive decisions satisfying a maximum risk of violating a safety envelope under uncertainty of other traffic participants' behavior and solve it using our variant of Multi-Agent Monte Carlo Tree Search. We demonstrate in simulation that our approach outperforms baselines approaches, and by reaching the specified violation risk level over driven simulation time, provides an interpretable and tunable safety objective for interactive planning.