A lot of efforts have been devoted to investigating how agents can learn effectively and achieve coordination in multiagent systems. However, it is still challenging in large-scale multiagent settings due to the complex dynamics between the environment and agents and the explosion of state-action space. In this paper, we design a novel Dynamic Multiagent Curriculum Learning (DyMA-CL) to solve large-scale problems by starting from learning on a multiagent scenario with a small size and progressively increasing the number of agents. We propose three transfer mechanisms across curricula to accelerate the learning process. Moreover, due to the fact that the state dimension varies across curricula,, and existing network structures cannot be applied in such a transfer setting since their network input sizes are fixed.

This paper presents a distributed, efficient, scalable and real-time motion planning algorithm for a large group of agents moving in 2 or 3-dimensional spaces. This algorithm enables autonomous agents to generate individual trajectories independently with only the relative position information of neighboring agents. Each agent applies a force-based control that contains two main terms: collision avoidance and navigational feedback. The first term keeps two agents separate with a certain distance, while the second term attracts each agent toward its goal location. Compared with existing collision-avoidance algorithms, the proposed force-based motion planning (FMP) algorithm is able to find collision-free motions with lower transition time, free from velocity state information of neighbouring agents. It leads to less computational overhead. The performance of proposed FMP is examined over several dense and complex 2D and 3D benchmark simulation scenarios, with results outperforming existing methods.

Arguably, intelligent agents ought to be able to discover their own questions so that in learning answers for them they learn unanticipated useful knowledge and skills; this departs from the focus in much of machine learning on agents learning answers to externally defined questions. We present a novel method for a reinforcement learning (RL) agent to discover questions formulated as general value functions or GVFs, a fairly rich form of knowledge representation. Specifically, our method uses non-myopic meta-gradients to learn GVF-questions such that learning answers to them, as an auxiliary task, induces useful representations for the main task faced by the RL agent. We demonstrate that auxiliary tasks based on the discovered GVFs are sufficient, on their own, to build representations that support main task learning, and that they do so better than popular hand-designed auxiliary tasks from the literature. Furthermore, we show, in the context of Atari 2600 videogames, how such auxiliary tasks, meta-learned alongside the main task, can improve the data efficiency of an actor-critic agent.

AI agents are increasingly deployed and used to make automated decisions that affect our lives on a daily basis. It is imperative to ensure that these systems embed ethical principles and respect human values. We focus on how we can attest to whether AI agents treat users fairly without discriminating against particular individuals or groups through biases in language. In particular, we discuss human unconscious biases, how they are embedded in language, and how AI systems inherit those biases by learning from and processing human language. Then, we outline a roadmap for future research to better understand and attest problematic AI biases derived from language.

The diversity of agent behaviors is an important topic for the quality of video games and virtual environments in general. Offering the most compelling experience for users with different skills is a difficult task, and usually needs important manual human effort for tuning existing code. This can get even harder when dealing with adaptive difficulty systems. Our paper's main purpose is to create a framework that can automatically create behaviors for game agents of different difficulty classes and enough diversity. In parallel with this, a second purpose is to create more automated tests for showing defects in the source code or possible logic exploits with less human effort.

Mixed cooperative-competitive control scenarios such as human-machine interaction with individual goals of the interacting partners are very challenging for reinforcement learning agents. In order to contribute towards intuitive human-machine collaboration, we focus on problems in the continuous state and control domain where no explicit communication is considered and the agents do not know the others' goals or control laws but only sense their control inputs retrospectively. Our proposed framework combines a learned partner model based on online data with a reinforcement learning agent that is trained in a simulated environment including the partner model. Thus, we overcome drawbacks of independent learners and, in addition, benefit from a reduced amount of real world data required for reinforcement learning which is vital in the human-machine context. We finally analyze an example that demonstrates the merits of our proposed framework which learns fast due to the simulated environment and adapts to the continuously changing partner due to the partner approximation. Keywords: Reinforcement Learning, Mixed Cooperative-Competitive Control, Opponent Modeling.

Bipartite b -matching, where agents on one side of a market are matched to one or more agents or items on the other, is a classical model that is used in myriad application areas such as healthcare, advertising, education, and genera l resource allocation. Traditionally, the primary goal of su ch models is to maximize a linear function of the constituent matches (e.g., linear social welfare maximization) subjec t to some constraints. Recent work has studied a new goal of balancing whole-match diversity and economic efficiency, where the objective is instead a monotone submodular function ove r the matching. These more general models are largely NPhard. In this work, we develop a combinatorial algorithm tha t constructs provably-optimal diverse b -matchings in pseudo-polynomial time. Then, we show how to extend our algorithm to solve new variations of the diverse b -matching problem. We then compare directly, on real-world datasets, against the state-of-the-art, quadratic-programming-based appr oach to solving diverse b -matching problems and show that our method outperforms it in both speed and (anytime) solution quality.

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games. OpenSpiel supports n-player (single- and multi- agent) zero-sum, cooperative and general-sum, one-shot and sequential, strictly turn-taking and simultaneous-move, perfect and imperfect information games, as well as traditional multiagent environments such as (partially- and fully- observable) grid worlds and social dilemmas. OpenSpiel also includes tools to analyze learning dynamics and other common evaluation metrics. Games are represented as procedural extensive-form games, with some natural extensions. The core API and games are implemented in C and exposed to Python.

CTU in Prague opens a competitive call for applications for fully-funded Ph.D. positions in the context of a recently awarded national center of excellence: Research Center for Informatics (RCI). RCI is the center of scientific excellence in computer science and artificial intelligence that boosts and integrates internationally competitive research conducted at Czech Technical University. The goal of RCI is to foster collaboration between the experts in different fields of computer science, between fundamental scientists and application-driven researchers, but chiefly between the experienced, internationally recognized, senior scientists and graduate students, postdocs and young assistant professors. RCI is focused on longer-term sustainability of excellence computer science and artificial intelligence. Research at RCI is focused on artificial intelligence, multiagent systems, game theory, automated planning, computational robotics with applications to cybersecurity, next-generation transportation systems, intelligent manufacturing, computer vision, machine learning, bioinformatics, computer graphics, embedded security, theoretical computer science or high-performance computing.

F ORCE FIELD TERMINOLOGY Taking into consideration a classical mechanics approach, a force is defined as a vectorial quantity that acts on a body to cause a change in its state of motion [25]. Forces can be classified in action-reaction (when bodies, which are in contact, change their momenta [25]) and action-at-a-distance forces (when objects interact without being physically touched). Considering that social interactions can be often modeled as contact-less, it becomes possible to explain social phenomena in a certain environment by modeling interactions between entities with action-at-a-distance forces. A force field null F is defined as a vector point-function which has the property that at every point of the space takes a particular value related to the magnitude and direction of a force acting on a particle of unit of mass placed there [26]. Accordingly, in this work, the particles of unit of mass affected by force fields will be called agents. A central force field null F f ( r)ˆr is a special case of force field in which the motion of agents is affected depending on the distance r to a center of force, which is generally associated with the center of mass of the object that produces the force field.