This paper presents a novel approach for autonomous cooperating UAVs in search and rescue operations in subterranean domains with complex topology. The proposed system was ranked second in the Virtual Track of the DARPA SubT Finals as part of the team CTU-CRAS-NORLAB. In contrast to the winning solution that was developed specifically for the Virtual Track, the proposed solution also proved to be a robust system for deployment onboard physical UAVs flying in the extremely harsh and confined environment of the real-world competition. The proposed approach enables fully autonomous and decentralized deployment of a UAV team with seamless simulation-to-world transfer, and proves its advantage over less mobile UGV teams in the flyable space of diverse environments. The main contributions of the paper are present in the mapping and navigation pipelines. The mapping approach employs novel map representations -- SphereMap for efficient risk-aware long-distance planning, FacetMap for surface coverage, and the compressed topological-volumetric LTVMap for allowing multi-robot cooperation under low-bandwidth communication. These representations are used in navigation together with novel methods for visibility-constrained informed search in a general 3D environment with no assumptions about the environment structure, while balancing deep exploration with sensor-coverage exploitation. The proposed solution also includes a visual-perception pipeline for on-board detection and localization of objects of interest in four RGB stream at 5 Hz each without a dedicated GPU. Apart from participation in the DARPA SubT, the performance of the UAV system is supported by extensive experimental verification in diverse environments with both qualitative and quantitative evaluation.

Optimal control seeks to find the best policy for an agent that optimizes a certain criterion. This general formulation allows optimal control theory to be applied in numerous areas such as robotics, finance, aeronautics, and many other fields. Inherently, optimal control optimizes the control of a single agent, but in recent years, extending optimal control problems to the realm of multi-agents has been a popular trend. Indeed, there are numerous cases where we want to model not just a single agent, but many, e.g. a fleet of drones. Here we introduce MASCOT: Multi-Agent Shape Control with Optimal Transport, a method to compute solutions to multi-agent optimal control problems that involve shape, formation, or density constraints among the agents. These constraints can be formulated in the running cost of the agents, or as a terminal cost, or even both. We first introduce the reader to optimal control and its multi-agent version. We then review the idea of optimal transport and Earth Mover's Distance. Finally, we demonstrate the method on some examples.

Optimization of human-AI teams hinges on the AI's ability to tailor its interaction to individual human teammates. A common hypothesis in adaptive AI research is that minor differences in people's predisposition to trust can significantly impact their likelihood of complying with recommendations from the AI. Predisposition to trust is often measured with self-report inventories that are administered before interactions. We benchmark a popular measure of this kind against behavioral predictors of compliance. We find that the inventory is a less effective predictor of compliance than the behavioral measures in datasets taken from three previous research projects. This suggests a general property that individual differences in initial behavior are more predictive than differences in self-reported trust attitudes. This result also shows a potential for easily accessible behavioral measures to provide an AI with more accurate models without the use of (often costly) survey instruments.

AI constructivism as inspired by Jean Piaget, described and surveyed by Frank Guerin, and representatively implemented by Gary Drescher seeks to create algorithms and knowledge structures that enable agents to acquire, maintain, and apply a deep understanding of the environment through sensorimotor interactions. This paper aims to increase awareness of constructivist AI implementations to encourage greater progress toward enabling lifelong learning by machines. It builds on Guerin's 2008 "Learning Like a Baby: A Survey of AI approaches." After briefly recapitulating that survey, it summarizes subsequent progress by the Guerin referents, numerous works not covered by Guerin (or found in other surveys), and relevant efforts in related areas. The focus is on knowledge representations and learning algorithms that have been used in practice viewed through lenses of Piaget's schemas, adaptation processes, and staged development. The paper concludes with a preview of a simple framework for constructive AI being developed by the author that parses concepts from sensory input and stores them in a semantic memory network linked to episodic data.

There is a recent trend of applying multi-agent reinforcement learning (MARL) to train an agent that can cooperate with humans in a zero-shot fashion without using any human data. The typical workflow is to first repeatedly run self-play (SP) to build a policy pool and then train the final adaptive policy against this pool. A crucial limitation of this framework is that every policy in the pool is optimized w.r.t. the environment reward function, which implicitly assumes that the testing partners of the adaptive policy will be precisely optimizing the same reward function as well. However, human objectives are often substantially biased according to their own preferences, which can differ greatly from the environment reward. We propose a more general framework, Hidden-Utility Self-Play (HSP), which explicitly models human biases as hidden reward functions in the self-play objective. By approximating the reward space as linear functions, HSP adopts an effective technique to generate an augmented policy pool with biased policies. We evaluate HSP on the Overcooked benchmark. Empirical results show that our HSP method produces higher rewards than baselines when cooperating with learned human models, manually scripted policies, and real humans. The HSP policy is also rated as the most assistive policy based on human feedback.

We consider the problem of episodic reinforcement learning where there are multiple stakeholders with different reward functions. Our goal is to output a policy that is socially fair with respect to different reward functions. Prior works have proposed different objectives that a fair policy must optimize including minimum welfare, and generalized Gini welfare. We first take an axiomatic view of the problem, and propose four axioms that any such fair objective must satisfy. We show that the Nash social welfare is the unique objective that uniquely satisfies all four objectives, whereas prior objectives fail to satisfy all four axioms. We then consider the learning version of the problem where the underlying model i.e. Markov decision process is unknown. We consider the problem of minimizing regret with respect to the fair policies maximizing three different fair objectives -- minimum welfare, generalized Gini welfare, and Nash social welfare. Based on optimistic planning, we propose a generic learning algorithm and derive its regret bound with respect to the three different policies. For the objective of Nash social welfare, we also derive a lower bound in regret that grows exponentially with $n$, the number of agents. Finally, we show that for the objective of minimum welfare, one can improve regret by a factor of $O(H)$ for a weaker notion of regret.

Offline reinforcement learning (offline RL) is an emerging field that has recently begun gaining attention across various application domains due to its ability to learn strategies from earlier collected datasets. Offline RL proved very successful, paving a path to solving previously intractable real-world problems, and we aim to generalize this paradigm to a multiplayer-game setting. To this end, we introduce a problem of offline equilibrium finding (OEF) and construct multiple types of datasets across a wide range of games using several established methods. To solve the OEF problem, we design a model-based framework that can directly apply any online equilibrium finding algorithm to the OEF setting while making minimal changes. The three most prominent contemporary online equilibrium finding algorithms are adapted to the context of OEF, creating three model-based variants: OEF-PSRO and OEF-CFR, which generalize the widely-used algorithms PSRO and Deep CFR to compute Nash equilibria (NEs), and OEF-JPSRO, which generalizes the JPSRO to calculate (Coarse) Correlated equilibria ((C)CEs). We also combine the behavior cloning policy with the model-based policy to further improve the performance and provide a theoretical guarantee of the solution quality. Extensive experimental results demonstrate the superiority of our approach over offline RL algorithms and the importance of using model-based methods for OEF problems. We hope our work will contribute to advancing research in large-scale equilibrium finding.

We consider many-to-one matching problems, where one side consists of students and the other side of schools with capacity constraints. We study how to optimally increase the capacities of the schools so as to obtain a stable and perfect matching (i.e., every student is matched) or a matching that is stable and Pareto-efficient for the students. We consider two common optimality criteria, one aiming to minimize the sum of capacity increases of all schools (abbrv. as MinSum) and the other aiming to minimize the maximum capacity increase of any school (abbrv. as MinMax). We obtain a complete picture in terms of computational complexity: Except for stable and perfect matchings using the MinMax criteria which is polynomial-time solvable, all three remaining problems are NP-hard. We further investigate the parameterized complexity and approximability and find that achieving stable and Pareto-efficient matchings via minimal capacity increases is much harder than achieving stable and perfect matchings.

Lateralization is ubiquitous in vertebrate brains which, as well as its role in locomotion, is considered an important factor in biological intelligence. Lateralization has been associated with both poor and good performance. It has been hypothesized that lateralization has benefits that may counterbalance its costs. Given that lateralization is ubiquitous, it likely has advantages that can benefit artificial intelligence. In turn, lateralized artificial intelligent systems can be used as tools to advance the understanding of lateralization in biological intelligence. Recently lateralization has been incorporated into artificially intelligent systems to solve complex problems in computer vision and navigation domains. Here we describe and test two novel lateralized artificial intelligent systems that simultaneously represent and address given problems at constituent and holistic levels. The experimental results demonstrate that the lateralized systems outperformed state-of-the-art non-lateralized systems in resolving complex problems. The advantages arise from the abilities, (i) to represent an input signal at both the constituent level and holistic level simultaneously, such that the most appropriate viewpoint controls the system; (ii) to avoid extraneous computations by generating excite and inhibit signals. The computational costs associated with the lateralized AI systems are either less than the conventional AI systems or countered by providing better solutions.

Fast and efficient transport protocols are the foundation of an increasingly distributed world. The burden of continuously delivering improved communication performance to support next-generation applications and services, combined with the increasing heterogeneity of systems and network technologies, has promoted the design of Congestion Control (CC) algorithms that perform well under specific environments. The challenge of designing a generic CC algorithm that can adapt to a broad range of scenarios is still an open research question. To tackle this challenge, we propose to apply a novel Reinforcement Learning (RL) approach. Our solution, MARLIN, uses the Soft Actor-Critic algorithm to maximize both entropy and return and models the learning process as an infinite-horizon task. We trained MARLIN on a real network with varying background traffic patterns to overcome the sim-to-real mismatch that researchers have encountered when applying RL to CC. We evaluated our solution on the task of file transfer and compared it to TCP Cubic. While further research is required, results have shown that MARLIN can achieve comparable results to TCP with little hyperparameter tuning, in a task significantly different from its training setting. Therefore, we believe that our work represents a promising first step toward building CC algorithms based on the maximum entropy RL framework.