We study the fairness of dynamic resource allocation problem under the $\alpha$-fairness criterion. We recognize two different fairness objectives that naturally arise in this problem: the well-understood slot-fairness objective that aims to ensure fairness at every timeslot, and the less explored horizon-fairness objective that aims to ensure fairness across utilities accumulated over a time horizon. We argue that horizon-fairness comes at a lower price in terms of social welfare. We study horizon-fairness with the regret as a performance metric and show that vanishing regret cannot be achieved in presence of an unrestricted adversary. We propose restrictions on the adversary's capabilities corresponding to realistic scenarios and an online policy that indeed guarantees vanishing regret under these restrictions. We demonstrate the applicability of the proposed fairness framework to a representative resource management problem considering a virtualized caching system where different caches cooperate to serve content requests.

Building autonomous agents able to grow open-ended repertoires of skills across their lives is a fundamental goal of artificial intelligence (AI). A promising developmental approach recommends the design of intrinsically motivated agents that learn new skills by generating and pursuing their own goals -- autotelic agents. But despite recent progress, existing algorithms still show serious limitations in terms of goal diversity, exploration, generalisation or skill composition. This perspective calls for the immersion of autotelic agents into rich socio-cultural worlds, an immensely important attribute of our environment that shapes human cognition but is mostly omitted in modern AI. Inspired by the seminal work of Vygotsky, we propose Vygotskian autotelic agents -- agents able to internalise their interactions with others and turn them into cognitive tools. We focus on language and show how its structure and informational content may support the development of new cognitive functions in artificial agents as it does in humans. We justify the approach by uncovering several examples of new artificial cognitive functions emerging from interactions between language and embodiment in recent works at the intersection of deep reinforcement learning and natural language processing. Looking forward, we highlight future opportunities and challenges for Vygotskian Autotelic AI research, including the use of language models as cultural models supporting artificial cognitive development.

Finding equilibria via gradient play in competitive multi-agent games has been attracting a growing amount of attention in recent years, with emphasis on designing efficient strategies where the agents operate in a decentralized and symmetric manner with guaranteed convergence. While significant efforts have been made in understanding zero-sum two-player matrix games, the performance in zero-sum multi-agent games remains inadequately explored, especially in the presence of delayed feedbacks, leaving the scalability and resiliency of gradient play open to questions. In this paper, we make progress by studying asynchronous gradient plays in zero-sum polymatrix games under delayed feedbacks. We first establish that the last iterate of entropy-regularized optimistic multiplicative weight updates (OMWU) method converges linearly to the quantal response equilibrium (QRE), the solution concept under bounded rationality, in the absence of delays. While the linear convergence continues to hold even when the feedbacks are randomly delayed under mild statistical assumptions, it converges at a noticeably slower rate due to a smaller tolerable range of learning rates. Moving beyond, we demonstrate entropy-regularized OMWU -- by adopting two-timescale learning rates in a delay-aware manner -- enjoys faster last-iterate convergence under fixed delays, and continues to converge provably even when the delays are arbitrarily bounded in an average-iterate manner. Our methods also lead to finite-time guarantees to approximate the Nash equilibrium (NE) by moderating the amount of regularization. To the best of our knowledge, this work is the first that aims to understand asynchronous gradient play in zero-sum polymatrix games under a wide range of delay assumptions, highlighting the role of learning rates separation.

In recent years, the role of artificially intelligent (AI) agents has evolved from being basic tools to socially intelligent agents working alongside humans towards common goals. In such scenarios, the ability to predict future behavior by observing past actions of their human teammates is highly desirable in an AI agent. Goal-oriented human behavior is complex, hierarchical, and unfolds across multiple timescales. Despite this observation, relatively little attention has been paid towards using multi-timescale features to model such behavior. In this paper, we propose an LSTM network architecture that processes behavioral information at multiple timescales to predict future behavior. We demonstrate that our approach for modeling behavior in multiple timescales substantially improves prediction of future behavior compared to methods that do not model behavior at multiple timescales. We evaluate our architecture on data collected in an urban search and rescue scenario simulated in a virtual Minecraft-based testbed, and compare its performance to that of a number of valid baselines as well as other methods that do not process inputs at multiple timescales.

In robotic networks relying on noisy range measurements between agents for cooperative localization, the achievable positioning accuracy strongly strongly depends on the network geometry. This motivates the problem of planning robot trajectories in such multi-robot systems in a way that maintains high localization accuracy. We present potential-based planning methods, where localizability potentials are introduced to characterize the quality of the network geometry for cooperative position estimation. These potentials are based on Cramer Rao Lower Bounds (CRLB) and provide a theoretical lower bound on the error covariance achievable by any unbiased position estimator. In the process, we establish connections between CRLBs and the theory of graph rigidity, which has been previously used to plan the motion of robotic networks. We develop decentralized deployment algorithms appropriate for large networks, and we use equality-constrained CRLBs to extend the concept of localizability to scenarios where additional information about the relative positions of the ranging sensors is known. We illustrate the resulting robot deployment methodology through simulated examples and an experiment.

This work presents AutoDRIVE, a comprehensive research and education platform for implementing and validating intelligent transportation algorithms pertaining to vehicular autonomy as well as smart city management. It is an openly accessible platform featuring a 1:14 scale car with realistic drive and steering actuators, redundant sensing modalities, high-performance computational resources, and standard vehicular lighting system. Additionally, the platform also offers a range of modules for rapid design and development of the infrastructure. The AutoDRIVE platform encompasses Devkit, Simulator and Testbed, a harmonious trio to develop, simulate and deploy autonomy algorithms. It is compatible with a variety of software development packages, and supports single as well as multi-agent paradigms through local and distributed computing. AutoDRIVE is a product-level implementation, with a vast scope for commercialization. This versatile platform has numerous applications, and they are bound to keep increasing as new features are added. This work demonstrates four such applications including autonomous parking, behavioural cloning, intersection traversal and smart city management, each exploiting distinct features of the platform.

The active inference framework (AIF) is a promising new computational framework grounded in contemporary neuroscience that can produce human-like behavior through reward-based learning. In this study, we test the ability for the AIF to capture the role of anticipation in the visual guidance of action in humans through the systematic investigation of a visual-motor task that has been well-explored -- that of intercepting a target moving over a ground plane. Previous research demonstrated that humans performing this task resorted to anticipatory changes in speed intended to compensate for semi-predictable changes in target speed later in the approach. To capture this behavior, our proposed "neural" AIF agent uses artificial neural networks to select actions on the basis of a very short term prediction of the information about the task environment that these actions would reveal along with a long-term estimate of the resulting cumulative expected free energy. Systematic variation revealed that anticipatory behavior emerged only when required by limitations on the agent's movement capabilities, and only when the agent was able to estimate accumulated free energy over sufficiently long durations into the future. In addition, we present a novel formulation of the prior function that maps a multi-dimensional world-state to a uni-dimensional distribution of free-energy. Together, these results demonstrate the use of AIF as a plausible model of anticipatory visually guided behavior in humans.

Multi-agent systems, automated reasoning, constraint processing and search, knowledge representation, machine learning, natural language, planning and scheduling, robotics and vision, and uncertainty ...

We derive optimal control policies for a Connected Automated Vehicle (CAV) and cooperating neighboring CAVs to carry out a lane change maneuver consisting of a longitudinal phase where the CAV properly positions itself relative to the cooperating neighbors and a lateral phase where it safely changes lanes. In contrast to prior work on this problem, where the CAV "selfishly" only seeks to minimize its maneuver time, we seek to ensure that the fast-lane traffic flow is minimally disrupted (through a properly defined metric). Additionally, when performing lane-changing maneuvers, we optimally select the cooperating vehicles from a set of feasible neighboring vehicles and experimentally show that the highway throughput is improved compared to the baseline case of human-driven vehicles changing lanes with no cooperation. When feasible solutions do not exist for a given maximal allowable disruption, we include a time relaxation method trading off a longer maneuver time with reduced disruption. Our analysis is also extended to multiple sequential maneuvers. Simulation results show the effectiveness of our controllers in terms of safety guarantees and up to 16% and 90% average throughput and maneuver time improvement respectively when compared to maneuvers with no cooperation.

Often the data that a model needs to be trained on is distributed among multiple computing agents and it cannot be accrued in a single server location because of logistical constraints such as memory, efficient data sharing means, or confidentiality requirements due to sensitive nature of the data. However, the need arises to train the same model with the entire distributed data. Isolated training individually by the agents with their local data may lead to overfitted models as the training data is limited. Besides, training such isolated models on different agents is redundant as more parameter updates have to be performed by the isolated models to reach a certain level of accuracy as compared to what can be achieved by sharing information. Distributed learning aims to leverage the full distributed data by a coordinated training among all the agents where the agents are allowed to share partial information (usually the learned model parameters or their gradients) without sharing any raw data.