In this paper, we propose a novel personalized decision support system that combines Theory of Mind (ToM) modeling and explainable Reinforcement Learning (XRL) to provide effective and interpretable interventions. Our method leverages DRL to provide expert action recommendations while incorporating ToM modeling to understand users' mental states and predict their future actions, enabling appropriate timing for intervention. To explain interventions, we use counterfactual explanations based on RL's feature importance and users' ToM model structure. Our proposed system generates accurate and personalized interventions that are easily interpretable by end-users. We demonstrate the effectiveness of our approach through a series of crowd-sourcing experiments in a simulated team decision-making task, where our system outperforms control baselines in terms of task performance. Our proposed approach is agnostic to task environment and RL model structure, therefore has the potential to be generalized to a wide range of applications.

Deception and persuasion play a critical role in long-horizon dialogues between multiple parties, especially when the interests, goals, and motivations of the participants are not aligned. Such complex tasks pose challenges for current Large Language Models (LLM) as deception and persuasion can easily mislead them, especially in long-horizon multi-party dialogues. To this end, we explore the game of Avalon: The Resistance, a social deduction game in which players must determine each other's hidden identities to complete their team's objective. We introduce an online testbed and a dataset containing 20 carefully collected and labeled games among human players that exhibit long-horizon deception in a cooperative-competitive setting. We discuss the capabilities of LLMs to utilize deceptive long-horizon conversations between six human players to determine each player's goal and motivation. Particularly, we discuss the multimodal integration of the chat between the players and the game's state that grounds the conversation, providing further insights into the true player identities. We find that even current state-of-the-art LLMs do not reach human performance, making our dataset a compelling benchmark to investigate the decision-making and language-processing capabilities of LLMs. Our dataset and online testbed can be found at our project website: https://sstepput.github.io/Avalon-NLU/

While Large Language Models (LLMs) have demonstrated impressive accomplishments in both reasoning and planning, their abilities in multi-agent collaborations remains largely unexplored. This study evaluates LLM-based agents in a multi-agent cooperative text game with Theory of Mind (ToM) inference tasks, comparing their performance with Multi-Agent Reinforcement Learning (MARL) and planning-based baselines. We observed evidence of emergent collaborative behaviors and high-order Theory of Mind capabilities among LLM-based agents. Our results reveal limitations in LLM-based agents' planning optimization due to systematic failures in managing long-horizon contexts and hallucination about the task state. We explore the use of explicit belief state representations to mitigate these issues, finding that it enhances task performance and the accuracy of ToM inferences for LLM-based agents.

Learning interpretable communication is essential for multi-agent and human-agent teams (HATs). In multi-agent reinforcement learning for partially-observable environments, agents may convey information to others via learned communication, allowing the team to complete its task. Inspired by human languages, recent works study discrete (using only a finite set of tokens) and sparse (communicating only at some time-steps) communication. However, the utility of such communication in human-agent team experiments has not yet been investigated. In this work, we analyze the efficacy of sparse-discrete methods for producing emergent communication that enables high agent-only and human-agent team performance. We develop agent-only teams that communicate sparsely via our scheme of Enforcers that sufficiently constrain communication to any budget. Our results show no loss or minimal loss of performance in benchmark environments and tasks. In human-agent teams tested in benchmark environments, where agents have been modeled using the Enforcers, we find that a prototype-based method produces meaningful discrete tokens that enable human partners to learn agent communication faster and better than a one-hot baseline. Additional HAT experiments show that an appropriate sparsity level lowers the cognitive load of humans when communicating with teams of agents and leads to superior team performance.

Teamwork is a set of interrelated reasoning, actions and behaviors of team members that facilitate common objectives. Teamwork theory and experiments have resulted in a set of states and processes for team effectiveness in both human-human and agent-agent teams. However, human-agent teaming is less well studied because it is so new and involves asymmetry in policy and intent not present in human teams. To optimize team performance in human-agent teaming, it is critical that agents infer human intent and adapt their polices for smooth coordination. Most literature in human-agent teaming builds agents referencing a learned human model. Though these agents are guaranteed to perform well with the learned model, they lay heavy assumptions on human policy such as optimality and consistency, which is unlikely in many real-world scenarios. In this paper, we propose a novel adaptive agent architecture in human-model-free setting on a two-player cooperative game, namely Team Space Fortress (TSF). Previous human-human team research have shown complementary policies in TSF game and diversity in human players' skill, which encourages us to relax the assumptions on human policy. Therefore, we discard learning human models from human data, and instead use an adaptation strategy on a pre-trained library of exemplar policies composed of RL algorithms or rule-based methods with minimal assumptions of human behavior. The adaptation strategy relies on a novel similarity metric to infer human policy and then selects the most complementary policy in our library to maximize the team performance. The adaptive agent architecture can be deployed in real-time and generalize to any off-the-shelf static agents. We conducted human-agent experiments to evaluate the proposed adaptive agent framework, and demonstrated the suboptimality, diversity, and adaptability of human policies in human-agent teams.

Recently, there has been increasing interest in transparency and interpretability in Deep Reinforcement Learning (DRL) systems. Verbal explanations, as the most natural way of communication in our daily life, deserve more attention, since they allow users to gain a better understanding of the system which ultimately could lead to a high level of trust and smooth collaboration. This paper reports a novel work in generating verbal explanations for DRL behaviors agent. A rule-based model is designed to construct explanations using a series of rules which are predefined with prior knowledge. A learning model is then proposed to expand the implicit logic of generating verbal explanation to general situations by employing rule-based explanations as training data. The learning model is shown to have better flexibility and generalizability than the static rule-based model. The performance of both models is evaluated quantitatively through objective metrics. The results show that verbal explanation generated by both models improve subjective satisfaction of users towards the interpretability of DRL systems. Additionally, seven variants of the learning model are designed to illustrate the contribution of input channels, attention mechanism, and proposed encoder in improving the quality of verbal explanation.

Autonomous AI systems will be entering human society in the near future to provide services and work alongside humans. For those systems to be accepted and trusted, the users should be able to understand the reasoning process of the system, i.e. the system should be transparent. System transparency enables humans to form coherent explanations of the system's decisions and actions. Transparency is important not only for user trust, but also for software debugging and certification. In recent years, Deep Neural Networks have made great advances in multiple application areas. However, deep neural networks are opaque. In this paper, we report on work in transparency in Deep Reinforcement Learning Networks (DRLN). Such networks have been extremely successful in accurately learning action control in image input domains, such as Atari games. In this paper, we propose a novel and general method that (a) incorporates explicit object recognition processing into deep reinforcement learning models, (b) forms the basis for the development of "object saliency maps", to provide visualization of internal states of DRLNs, thus enabling the formation of explanations and (c) can be incorporated in any existing deep reinforcement learning framework. We present computational results and human experiments to evaluate our approach.

The Association for the Advancement of Artificial Intelligence was pleased to present the 2012 Fall Symposium Series, held Friday through Sunday, November 2–4, at the Westin Arlington Gateway in Arlington, Virginia. The titles of the eight symposia were as follows: AI for Gerontechnology (FS-12-01), Artificial Intelligence of Humor (FS-12-02), Discovery Informatics: The Role of AI Research in Innovating Scientific Processes (FS-12-03), Human Control of Bio-Inspired Swarms (FS-12-04), Information Retrieval and Knowledge Discovery in Biomedical Text (FS-12-05), Machine Aggregation of Human Judgment (FS-12-06), Robots Learning Interactively from Human Teachers (FS-12-07), and Social Networks and Social Contagion (FS-12-08). The highlights of each symposium are presented in this report.

The Association for the Advancement of Artificial Intelligence was pleased to present the 2012 Fall Symposium Series, held Friday through Sunday, November 2–4, at the Westin Arlington Gateway in Arlington, Virginia. The titles of the eight symposia were as follows: AI for Gerontechnology (FS-12-01), Artificial Intelligence of Humor (FS-12-02), Discovery Informatics: The Role of AI Research in Innovating Scientific Processes (FS-12-03), Human Control of Bio-Inspired Swarms (FS-12-04), Information Retrieval and Knowledge Discovery in Biomedical Text (FS-12-05), Machine Aggregation of Human Judgment (FS-12-06), Robots Learning Interactively from Human Teachers (FS-12-07), and Social Networks and Social Contagion (FS-12-08). The highlights of each symposium are presented in this report.

In practical applications of robot swarms with bio-inspired behaviors, a human operator will need to exert control over the swarm to fulfill the mission objectives. In many operational settings, human operators are remotely located and the communication environment is harsh. Hence, there exists some latency in information (or control command) transfer between the human and the swarm. In this paper, we conduct experiments of human-swarm interaction to investigate the effects of communication latency on the performance of a human-swarm system in a swarm foraging task. We develop and investigate the concept of neglect benevolence, where a human operator allows the swarm to evolve on its own and stabilize before giving new commands. Our experimental results indicate that operators exploited neglect benevolence in different ways to develop successful strategies in the foraging task. Furthermore, we show experimentally that the use of a predictive display can help mitigate the adverse effects of communication latency.