Full automation is often not achievable or desirable in critical systems with high-stakes decisions. Instead, human-AI teams can achieve better results. To research, develop, evaluate, and validate algorithms suited for such teaming, lightweight experimentation platforms that enable interactions between humans and multiple AI agents are necessary. However, there are limited examples of such platforms for defense environments. To address this gap, we present the Cogment human-machine teaming experimentation platform, which implements human-machine teaming (HMT) use cases that features heterogeneous multi-agent systems and can involve learning AI agents, static AI agents, and humans. It is built on the Cogment platform and has been used for academic research, including work presented at the ALA workshop at AAMAS this year [1]. With this platform, we hope to facilitate further research on human-machine teaming in critical systems and defense environments.

Advancements in machine learning and artificial intelligence are transforming materials discovery. Yet, the availability of structured experimental data remains a bottleneck. The vast corpus of scientific literature presents a valuable and rich resource of such data. However, manual dataset creation from these resources is challenging due to issues in maintaining quality and consistency, scalability limitations, and the risk of human error and bias. Therefore, in this work, we develop a chemist AI agent, powered by large language models (LLMs), to overcome these challenges by autonomously creating structured datasets from natural language text, ranging from sentences and paragraphs to extensive scientific research articles. Our chemist AI agent, Eunomia, can plan and execute actions by leveraging the existing knowledge from decades of scientific research articles, scientists, the Internet and other tools altogether. We benchmark the performance of our approach in three different information extraction tasks with various levels of complexity, including solid-state impurity doping, metal-organic framework (MOF) chemical formula, and property relations. Our results demonstrate that our zero-shot agent, with the appropriate tools, is capable of attaining performance that is either superior or comparable to the state-of-the-art fine-tuned materials information extraction methods. This approach simplifies compilation of machine learning-ready datasets for various materials discovery applications, and significantly ease the accessibility of advanced natural language processing tools for novice users in natural language. The methodology in this work is developed as an open-source software on https://github.com/AI4ChemS/Eunomia.

The maturation of cognition, from introspection to understanding others, has long been a hallmark of human development. This position paper posits that for AI systems to truly emulate or approach human-like interactions, especially within multifaceted environments populated with diverse agents, they must first achieve an in-depth and nuanced understanding of self. Drawing parallels with the human developmental trajectory from self-awareness to mentalizing (also called theory of mind), the paper argues that the quality of an autonomous agent's introspective capabilities of self are crucial in mirroring quality human-like understandings of other agents. While counterarguments emphasize practicality, computational efficiency, and ethical concerns, this position proposes a development approach, blending algorithmic considerations of self-referential processing. Ultimately, the vision set forth is not merely of machines that compute but of entities that introspect, empathize, and understand, harmonizing with the complex compositions of human cognition.

Novelty adaptation is the ability of an intelligent agent to adjust its behavior in response to changes in its environment. This is an important characteristic of intelligent agents, as it allows them to continue to function effectively in novel or unexpected situations, but still stands as a critical challenge for deep reinforcement learning (DRL). To tackle this challenge, we propose a simple yet effective novel method, NAPPING (Novelty Adaptation Principles Learning), that allows trained DRL agents to respond to different classes of novelties in open worlds rapidly. With NAPPING, DRL agents can learn to adjust the trained policy only when necessary. They can quickly generalize to similar novel situations without affecting the part of the trained policy that still works. To demonstrate the efficiency and efficacy of NAPPING, we evaluate our method on four action domains that are different in reward structures and the type of task. The domains are CartPole and MountainCar (classic control), CrossRoad (path-finding), and AngryBirds (physical reasoning). We compare NAPPING with standard online and fine-tuning DRL methods in CartPole, MountainCar and CrossRoad, and state-of-the-art methods in the more complicated AngryBirds domain. Our evaluation results demonstrate that with our proposed method, DRL agents can rapidly and effectively adjust to a wide range of novel situations across all tested domains.

Nash equilibrium is one of the most influential solution concepts in game theory. With the development of computer science and artificial intelligence, there is an increasing demand on Nash equilibrium computation, especially for Internet economics and multi-agent learning. This paper reviews various algorithms computing the Nash equilibrium and its approximation solutions in finite normal-form games from both theoretical and empirical perspectives. For the theoretical part, we classify algorithms in the literature and present basic ideas on algorithm design and analysis. For the empirical part, we present a comprehensive comparison on the algorithms in the literature over different kinds of games. Based on these results, we provide practical suggestions on implementations and uses of these algorithms. Finally, we present a series of open problems from both theoretical and practical considerations.

Many complicated real-world tasks can be broken down into smaller, more manageable parts, and planning with prior knowledge extracted from these simplified pieces is crucial for humans to make accurate decisions. However, replicating this process remains a challenge for AI agents and naturally raises two questions: How to extract discriminative knowledge representation from priors? How to develop a rational plan to decompose complex problems? Most existing representation learning methods employing a single encoder structure are fragile and sensitive to complex and diverse dynamics. To address this issue, we introduce a multiple-encoder and individual-predictor regime to learn task-essential representations from sufficient data for simple subtasks. Multiple encoders can extract adequate task-relevant dynamics without confusion, and the shared predictor can discriminate the task characteristics. We also use the attention mechanism to generate a top-k subtask planning tree, which customizes subtask execution plans in guiding complex decisions on unseen tasks. This process enables forward-looking and globality by flexibly adjusting the depth and width of the planning tree. Empirical results on a challenging platform composed of some basic simple tasks and combinatorially rich synthetic tasks consistently outperform some competitive baselines and demonstrate the benefits of our design.

This paper proposes a distributed guiding-vector-field (DGVF) controller for cross-domain unmanned systems (CDUSs) consisting of heterogeneous unmanned aerial vehicles (UAVs) and unmanned surface vehicles (USVs), to achieve coordinated navigation whereas maneuvering along their prescribed paths. In particular, the DGVF controller provides a hierarchical architecture of an upper-level heterogeneous guidance velocity controller and a lower-level signal tracking regulator. Therein, the upper-level controller is to govern multiple heterogeneous USVs and UAVs to approach and maneuver along the prescribed paths and coordinate the formation simultaneously, whereas the low-level regulator is to track the corresponding desired guidance signals provided by the upper-level module. Significantly, the heterogeneous coordination among neighboring UAVs and USVs is achieved merely by the lightweight communication of a scalar (i.e., the additional virtual coordinate), which substantially decreases the communication and computational costs. Sufficient conditions assuring asymptotical convergence of the closed-loop system are derived in presence of the exponentially vanishing tracking errors. Finally, real-lake experiments are conducted on a self-established cross-domain heterogeneous platform consisting of three M-100 UAVs, two HUSTER-16 USVs, a HUSTER-12C USV, and a WiFi 5G wireless communication station to verify the effectiveness of the present DGVF controller.

We present a nonparametric statistical test for determining whether an agent is following a given mixed strategy in a repeated strategic-form game given samples of the agent's play. This involves two components: determining whether the agent's frequencies of pure strategies are sufficiently close to the target frequencies, and determining whether the pure strategies selected are independent between different game iterations. Our integrated test involves applying a chi-squared goodness of fit test for the first component and a generalized Wald-Wolfowitz runs test for the second component. The results from both tests are combined using Bonferroni correction to produce a complete test for a given significance level $\alpha.$ We applied the test to publicly available data of human rock-paper-scissors play. The data consists of 50 iterations of play for 500 human players. We test with a null hypothesis that the players are following a uniform random strategy independently at each game iteration. Using a significance level of $\alpha = 0.05$, we conclude that 305 (61%) of the subjects are following the target strategy.

Communication is crucial for solving cooperative Multi-Agent Reinforcement Learning tasks in partially observable Markov Decision Processes. Existing works often rely on black-box methods to encode local information/features into messages shared with other agents, leading to the generation of continuous messages with high communication overhead and poor interpretability. Prior attempts at discrete communication methods generate one-hot vectors trained as part of agents' actions and use the Gumbel softmax operation for calculating message gradients, which are all heuristic designs that do not provide any quantitative guarantees on the expected return. This paper establishes an upper bound on the return gap between an ideal policy with full observability and an optimal partially observable policy with discrete communication. This result enables us to recast multi-agent communication into a novel online clustering problem over the local observations at each agent, with messages as cluster labels and the upper bound on the return gap as clustering loss. To minimize the return gap, we propose the Return-Gap-Minimization Communication (RGMComm) algorithm, which is a surprisingly simple design of discrete message generation functions and is integrated with reinforcement learning through the utilization of a novel Regularized Information Maximization loss function, which incorporates cosine-distance as the clustering metric. Evaluations show that RGMComm significantly outperforms state-of-the-art multi-agent communication baselines and can achieve nearly optimal returns with few-bit messages that are naturally interpretable.

We study worst-case VCG redistribution mechanism design for the public project problem. We use a multilayer perceptron (MLP) with ReLU activation to model the payment function and use mixed integer programming (MIP) to solve for the worst-case type profiles that maximally violate the mechanism design constraints. We collect these worst-case type profiles and use them as training samples to train toward better worst-case mechanisms. In practice, we require a tiny network structure for the above approach to scale. The Lottery Ticket Hypothesis states that a large network is likely to contain a "winning ticket" -- a much smaller subnetwork that "won the initialization lottery", which makes its training particularly effective. Motivated by this hypothesis, we train a large network and prune it into a tiny subnetwork. We run MIP-based worst-case training on the drawn subnetwork and evaluate the resulting mechanism's worst-case performance. If the subnetwork does not achieve good worst-case performance, then we record the type profiles that cause the current draw to be bad. To draw again, we restore the large network to its initial weights and prune using recorded type profiles from earlier draws, therefore avoiding drawing the same ticket twice. We expect to eventually encounter a tiny subnetwork that leads to effective training for our worst-case mechanism design task. Lastly, a by-product of multiple ticket draws is an ensemble of mechanisms with different worst cases, which improves the worst-case performance further. Using our approach, we find previously unknown optimal mechanisms for up to 5 agents. Our results confirm the tightness of existing theoretical upper bounds. For up to 20 agents, we derive significantly improved worst-case mechanisms, surpassing a long list of existing manual results.