Learning to collaborate is critical in Multi-Agent Reinforcement Learning (MARL). Previous works promote collaboration by maximizing the correlation of agents' behaviors, which is typically characterized by Mutual Information (MI) in different forms. However, we reveal sub-optimal collaborative behaviors also emerge with strong correlations, and simply maximizing the MI can, surprisingly, hinder the learning towards better collaboration. To address this issue, we propose a novel MARL framework, called Progressive Mutual Information Collaboration (PMIC), for more effective MI-driven collaboration. PMIC uses a new collaboration criterion measured by the MI between global states and joint actions. Based on this criterion, the key idea of PMIC is maximizing the MI associated with superior collaborative behaviors and minimizing the MI associated with inferior ones. The two MI objectives play complementary roles by facilitating better collaborations while avoiding falling into sub-optimal ones. Experiments on a wide range of MARL benchmarks show the superior performance of PMIC compared with other algorithms.

Abstract--Planning the evacuation of people from crowded places, such as squares, stadiums, or indoor arenas during emergency scenarios is a fundamental task that authorities must deal with. This article summarizes the work of the authors to simulate an emergency scenario in a square using NetLogo, a multi-agent programmable modeling environment. The emergency scenario is based on a real event, which took place in Piazza San Carlo, Turin, on the 3rd of June 2017. The authors have developed a model and conducted various experiments, the results of which are presented, discussed and analyzed. The article concludes by offering suggestions for further research and summarizing the key takeaways.

In each round of a Swiss-system tournament, players of similar score are paired against each other. An intentional early loss therefore might lead to weaker opponents in later rounds and thus to a better final tournament result - a phenomenon known as the Swiss Gambit. To the best of our knowledge it is an open question whether this strategy can actually work. This paper provides answers based on an empirical agent-based analysis for the most prominent application area of the Swiss-system format, namely chess tournaments. We simulate realistic tournaments by employing the official FIDE pairing system for computing the player pairings in each round. We show that even though gambits are widely possible in Swiss-system chess tournaments, profiting from them requires a high degree of predictability of match results. Moreover, even if a Swiss Gambit succeeds, the obtained improvement in the final ranking is limited. Our experiments prove that counting on a Swiss Gambit is indeed a lot more of a risky gambit than a reliable strategy to improve the final rank.

In this work, we ask for and answer what makes classical temporal-difference reinforcement learning with epsilon-greedy strategies cooperative. Cooperating in social dilemma situations is vital for animals, humans, and machines. While evolutionary theory revealed a range of mechanisms promoting cooperation, the conditions under which agents learn to cooperate are contested. Here, we demonstrate which and how individual elements of the multi-agent learning setting lead to cooperation. We use the iterated Prisoner's dilemma with one-period memory as a testbed. Each of the two learning agents learns a strategy that conditions the following action choices on both agents' action choices of the last round. We find that next to a high caring for future rewards, a low exploration rate, and a small learning rate, it is primarily intrinsic stochastic fluctuations of the reinforcement learning process which double the final rate of cooperation to up to 80%. Thus, inherent noise is not a necessary evil of the iterative learning process. It is a critical asset for the learning of cooperation. However, we also point out the trade-off between a high likelihood of cooperative behavior and achieving this in a reasonable amount of time. Our findings are relevant for purposefully designing cooperative algorithms and regulating undesired collusive effects.

Safety in goal directed Reinforcement Learning (RL) settings has typically been handled through constraints over trajectories and have demonstrated good performance in primarily short horizon tasks (goal is not too far away). In this paper, we are specifically interested in the problem of solving temporally extended decision making problems such as (1) robots that have to clean different areas in a house while avoiding slippery and unsafe areas (e.g., stairs) and retaining enough charge to move to a charging dock; (2) autonomous electric vehicles that have to reach a far away destination while having to optimize charging locations along the way; in the presence of complex safety constraints. Our key contribution is a (safety) Constrained Planning with Reinforcement Learning (CoP-RL) mechanism that combines a high-level constrained planning agent (which computes a reward maximizing path from a given start to a far away goal state while satisfying cost constraints) with a low-level goal conditioned RL agent (which estimates cost and reward values to move between nearby states). A major advantage of CoP-RL is that it can handle constraints on the cost value distribution (e.g., on Conditional Value at Risk, CVaR, and also on expected value). We perform extensive experiments with different types of safety constraints to demonstrate the utility of our approach over leading best approaches in constrained and hierarchical RL.

Trajectory prediction is an important task to support safe and intelligent behaviours in autonomous systems. Many advanced approaches have been proposed over the years with improved spatial and temporal feature extraction. However, human behaviour is naturally multimodal and uncertain: given the past trajectory and surrounding environment information, an agent can have multiple plausible trajectories in the future. To tackle this problem, an essential task named multimodal trajectory prediction (MTP) has recently been studied, which aims to generate a diverse, acceptable and explainable distribution of future predictions for each agent. In this paper, we present the first survey for MTP with our unique taxonomies and comprehensive analysis of frameworks, datasets and evaluation metrics. In addition, we discuss multiple future directions that can help researchers develop novel multimodal trajectory prediction systems.

Task allocation in heterogeneous multi-agent teams often requires reasoning about multi-dimensional agent traits (i.e., capabilities) and the demands placed on them by tasks. However, existing methods tend to ignore the fact that not all traits equally contribute to a given task. Ignoring such inherent preferences or relative importance can lead to unintended sub-optimal allocations of limited agent resources that do not necessarily contribute to task success. Further, reasoning over a large number of traits can incur a hefty computational burden. To alleviate these concerns, we propose an algorithm to infer task-specific trait preferences implicit in expert demonstrations. We leverage the insight that the consistency with which an expert allocates a trait to a task across demonstrations reflects the trait's importance to that task. Inspired by findings in psychology, we account for the fact that the inherent diversity of a trait in the dataset influences the dataset's informativeness and, thereby, the extent of the inferred preference or the lack thereof. Through detailed numerical simulations and evaluations of a publicly-available soccer dataset (FIFA 20), we demonstrate that we can successfully infer implicit trait preferences and that accounting for the inferred preferences leads to more computationally efficient and effective task allocation, compared to a baseline approach that treats all traits equally.

Feature selection is an effective preprocessing technique to reduce data dimension. For feature selection, rough set theory provides many measures, among which mutual information is one of the most important attribute measures. However, mutual information based importance measures are computationally expensive and inaccurate, especially in hypersample instances, and it is undoubtedly a NP-hard problem in high-dimensional hyperhigh-dimensional data sets. Although many representative group intelligent algorithm feature selection strategies have been proposed so far to improve the accuracy, there is still a bottleneck when using these feature selection algorithms to process high-dimensional large-scale data sets, which consumes a lot of performance and is easy to select weakly correlated and redundant features. In this study, we propose an incremental mutual information based improved swarm intelligent optimization method (IMIICSO), which uses rough set theory to calculate the importance of feature selection based on mutual information. This method extracts decision table reduction knowledge to guide group algorithm global search. By exploring the computation of mutual information of supersamples, we can not only discard the useless features to speed up the internal and external computation, but also effectively reduce the cardinality of the optimal feature subset by using IMIICSO method, so that the cardinality is minimized by comparison. The accuracy of feature subsets selected by the improved cockroach swarm algorithm based on incremental mutual information is better or almost the same as that of the original swarm intelligent optimization algorithm. Experiments using 10 datasets derived from UCI, including large scale and high dimensional datasets, confirmed the efficiency and effectiveness of the proposed algorithm.

Swarm robotics provides an approach to the coordination of large numbers of robots inspired by swarm behaviours in nature [1]. The overall behaviours of a swarm are not explicitly engineered in the system. Instead, they are an emergent consequence of the interactions of individual agents with each other and the environment [2]; this poses a challenge to assurance. According to the ISO standard for systems and software engineering vocabulary [3], assurance is defined as "all the planned and systematic activities implemented within the quality system, and demonstrated as needed, to provide adequate confidence that an entity will fulfil requirements for quality". Assurance tasks comprise conformance to standards, verification and validation (V&V), and certification. Assurance criteria for autonomous systems (AS) include both functional and non-functional requirements such as safety [4]. Existing standards and regulations of AS are either implicitly or explicitly based on the V lifecycle model [5], which moves from requirements through design onto implementation and testing before deployment [6, 7]. However, this model is unlikely to be suitable for systems with emergent behaviour (EB); for example through interaction with other agents and the environment, as is the case with swarms. ISO standards have been developed for the service robotics sector (non-industrial) (e.g.

We initiate the study of how to perturb the reward in a zero-sum Markov game with two players to induce a desirable Nash equilibrium, namely arbitrating. Such a problem admits a bi-level optimization formulation. The lower level requires solving the Nash equilibrium under a given reward function, which makes the overall problem challenging to optimize in an end-to-end way. We propose a backpropagation scheme that differentiates through the Nash equilibrium, which provides the gradient feedback for the upper level. In particular, our method only requires a black-box solver for the (regularized) Nash equilibrium (NE). We develop the convergence analysis for the proposed framework with proper black-box NE solvers and demonstrate the empirical successes in two multi-agent reinforcement learning (MARL) environments.