It poses technical difficulty to achieve stable tracking even for single mismatched nonlinear strict-feedback systems when intermittent state feedback is utilized. The underlying problem becomes even more complicated if such systems are networked with directed communication and state-triggering setting. In this work, we present a fully distributed neuroadaptive tracking control scheme for multiple agent systems in strict-feedback form using triggered state from the agent itself and the triggered states from the neighbor agents. To circumvent the non-differentiability of virtual controllers stemming from state-triggering, we first develop a distributed continuous control scheme under regular state feedback, upon which we construct the distributed event-triggered control scheme by replacing the states in the preceding scheme with the triggered ones. Several useful lemmas are introduced to allow the stability condition to be established with such replacement, ensuring that all the closed-loop signals are semi-globally uniformly ultimately bounded (SGUUB), with the output tracking error converging to a residual set around zero. Besides, with proper choices of the design parameters, the tracking performance in the mean square sense can be improved. Numerical simulation verifies the benefits and efficiency of the proposed method.

Recent neural generation systems have demonstrated the potential for procedurally generating game content, images, stories, and more. However, most neural generation algorithms are "uncontrolled" in the sense that the user has little say in creative decisions beyond the initial prompt specification. Co-creative, mixed-initiative systems require user-centric means of influencing the algorithm, especially when users are unlikely to have machine learning expertise. The key to co-creative systems is the ability to communicate ideas and intent from the user to the agent, as well as from the agent to the user. Key questions in co-creative AI include: How can users express their creative intentions? How can creative AI systems communicate their beliefs, explain their moves, or instruct users to act on their behalf? When should creative AI systems take initiative? The answer to such questions and more will enable us to develop better co-creative systems that make humans more capable of expressing their creative intents. We introduce CREATIVE-WAND, a customizable framework for investigating co-creative mixed-initiative generation. CREATIVE-WAND enables plug-and-play injection of generative models and human-agent communication channels into a chat-based interface. It provides a number of dimensions along which an AI generator and humans can communicate during the co-creative process. We illustrate the CREATIVE-WAND framework by using it to study one dimension of co-creative communication-global versus local creative intent specification by the user-in the context of storytelling.

Dynamical systems across many disciplines are modeled as interacting particles or agents, with interaction rules that depend on a very small number of variables (e.g. pairwise distances, pairwise differences of phases, etc...), functions of the state of pairs of agents. Yet, these interaction rules can generate self-organized dynamics, with complex emergent behaviors (clustering, flocking, swarming, etc.). We propose a learning technique that, given observations of states and velocities along trajectories of the agents, yields both the variables upon which the interaction kernel depends and the interaction kernel itself, in a nonparametric fashion. This yields an effective dimension reduction which avoids the curse of dimensionality from the high-dimensional observation data (states and velocities of all the agents). We demonstrate the learning capability of our method to a variety of first-order interacting systems.

Controlling a distributed autonomous unmanned aerial vehicle (UAV) formation is usually considered in the context of recovering the connectivity graph should a single UAV agent be lost. At the same time, little focus is made on how such loss affects the dynamics of the formation as a system. To compensate for the negative effects, we propose an adaptation algorithm that reduces the increasing interaction between the UAV agents that remain in the formation. This algorithm enables the autonomous system to adjust to the new equilibrium state. The algorithm has been tested by computer simulation on full nonlinear UAV models. Simulation results prove the negative effect (the increased final cruising speed of the formation) to be completely eliminated.

We examine global non-asymptotic convergence properties of policy gradient methods for multi-agent reinforcement learning (RL) problems in Markov potential games (MPG). To learn a Nash equilibrium of an MPG in which the size of state space and/or the number of players can be very large, we propose new independent policy gradient algorithms that are run by all players in tandem. When there is no uncertainty in the gradient evaluation, we show that our algorithm finds an $\epsilon$-Nash equilibrium with $O(1/\epsilon^2)$ iteration complexity which does not explicitly depend on the state space size. When the exact gradient is not available, we establish $O(1/\epsilon^5)$ sample complexity bound in a potentially infinitely large state space for a sample-based algorithm that utilizes function approximation. Moreover, we identify a class of independent policy gradient algorithms that enjoys convergence for both zero-sum Markov games and Markov cooperative games with the players that are oblivious to the types of games being played. Finally, we provide computational experiments to corroborate the merits and the effectiveness of our theoretical developments.

To collaborate well with robots, we must be able to understand their decision making. Humans naturally infer other agents' beliefs and desires by reasoning about their observable behavior in a way that resembles inverse reinforcement learning (IRL). Thus, robots can convey their beliefs and desires by providing demonstrations that are informative for a human learner's IRL. An informative demonstration is one that differs strongly from the learner's expectations of what the robot will do given their current understanding of the robot's decision making. However, standard IRL does not model the learner's existing expectations, and thus cannot do this counterfactual reasoning. We propose to incorporate the learner's current understanding of the robot's decision making into our model of human IRL, so that a robot can select demonstrations that maximize the human's understanding. We also propose a novel measure for estimating the difficulty for a human to predict instances of a robot's behavior in unseen environments. A user study finds that our test difficulty measure correlates well with human performance and confidence. Interestingly, considering human beliefs and counterfactuals when selecting demonstrations decreases human performance on easy tests, but increases performance on difficult tests, providing insight on how to best utilize such models.

Stochastic gradient descent (SGD) algorithm is an effective learning strategy to build a latent factor analysis (LFA) model on a high-dimensional and incomplete (HDI) matrix. A particle swarm optimization (PSO) algorithm is commonly adopted to make an SGD-based LFA model's hyper-parameters, i.e, learning rate and regularization coefficient, self-adaptation. However, a standard PSO algorithm may suffer from accuracy loss caused by premature convergence. To address this issue, this paper incorporates more historical information into each particle's evolutionary process for avoiding premature convergence following the principle of a generalized-momentum (GM) method, thereby innovatively achieving a novel GM-incorporated PSO (GM-PSO). With it, a GM-PSO-based LFA (GMPL) model is further achieved to implement efficient self-adaptation of hyper-parameters. The experimental results on three HDI matrices demonstrate that the GMPL model achieves a higher prediction accuracy for missing data estimation in industrial applications.

We study multi-agent reinforcement learning (MARL) with centralized training and decentralized execution. During the training, new agents may join, and existing agents may unexpectedly leave the training. In such situations, a standard deep MARL model must be trained again from scratch, which is very time-consuming. To tackle this problem, we propose a special network architecture with a few-shot learning algorithm that allows the number of agents to vary during centralized training. In particular, when a new agent joins the centralized training, our few-shot learning algorithm trains its policy network and value network using a small number of samples; when an agent leaves the training, the training process of the remaining agents is not affected. Our experiments show that using the proposed network architecture and algorithm, model adaptation when new agents join can be 100+ times faster than the baseline. Our work is applicable to any setting, including cooperative, competitive, and mixed.

Computing Nash equilibrium policies is a central problem in multi-agent reinforcement learning that has received extensive attention both in theory and in practice. However, provable guarantees have been thus far either limited to fully competitive or cooperative scenarios or impose strong assumptions that are difficult to meet in most practical applications. In this work, we depart from those prior results by investigating infinite-horizon \emph{adversarial team Markov games}, a natural and well-motivated class of games in which a team of identically-interested players -- in the absence of any explicit coordination or communication -- is competing against an adversarial player. This setting allows for a unifying treatment of zero-sum Markov games and Markov potential games, and serves as a step to model more realistic strategic interactions that feature both competing and cooperative interests. Our main contribution is the first algorithm for computing stationary $\epsilon$-approximate Nash equilibria in adversarial team Markov games with computational complexity that is polynomial in all the natural parameters of the game, as well as $1/\epsilon$. The proposed algorithm is particularly natural and practical, and it is based on performing independent policy gradient steps for each player in the team, in tandem with best responses from the side of the adversary; in turn, the policy for the adversary is then obtained by solving a carefully constructed linear program. Our analysis leverages non-standard techniques to establish the KKT optimality conditions for a nonlinear program with nonconvex constraints, thereby leading to a natural interpretation of the induced Lagrange multipliers. Along the way, we significantly extend an important characterization of optimal policies in adversarial (normal-form) team games due to Von Stengel and Koller (GEB `97).

Finite-time motion planning with collision avoidance is a challenging issue in multi-agent systems. This paper proposes a novel distributed controller based on a new Lyapunov barrier function which guarantees finite-time stability for multi-agent systems without collisions. First, the problem of finite-time motion planning of multi-agent systems is formulated. Then, a novel finite-time distributed controller is developed based on a Lyapunov barrier function. Finally, numerical simulations demonstrate the effectiveness of proposed method.