We study N-player finite games with costs perturbed due to time-varying disturbances in the underlying system and to that end we propose the concept of Robust Correlated Equilibrium that generalizes the definition of Correlated Equilibrium. Conditions under which the Robust Correlated Equilibrium exists are specified and a decentralized algorithm for learning strategies that are optimal in the sense of Robust Correlated Equilibrium is proposed. The primary contribution of the paper is the convergence analysis of the algorithm and to that end, we propose an extension of the celebrated Blackwell's Approachability theorem to games with costs that are not just time-average as in the original Blackwell's Approachability Theorem but also include time-average of previous algorithm iterates. The designed algorithm is applied to a practical water distribution network with pumps being the controllers and their costs being perturbed by uncertain consumption by consumers. Simulation results show that each controller achieves no regret and empirical distributions converge to the Robust Correlated Equilibrium.

Decentralized coordination for multi-robot systems involves planning in challenging, high-dimensional spaces. The planning problem is particularly challenging in the presence of obstacles and different sources of uncertainty such as inaccurate dynamic models and sensor noise. In this paper, we introduce Stein Variational Belief Propagation (SVBP), a novel algorithm for performing inference over nonparametric marginal distributions of nodes in a graph. We apply SVBP to multi-robot coordination by modelling a robot swarm as a graphical model and performing inference for each robot. We demonstrate our algorithm on a simulated multi-robot perception task, and on a multi-robot planning task within a Model-Predictive Control (MPC) framework, on both simulated and real-world mobile robots. Our experiments show that SVBP represents multi-modal distributions better than sampling-based or Gaussian baselines, resulting in improved performance on perception and planning tasks. Furthermore, we show that SVBP's ability to represent diverse trajectories for decentralized multi-robot planning makes it less prone to deadlock scenarios than leading baselines.

In economic modeling, there has been an increasing investigation into multi-agent simulators. Nevertheless, state-of-the-art studies establish the model based on reinforcement learning (RL) exclusively for specific agent categories, e.g., households, firms, or the government. It lacks concerns over the resulting adaptation of other pivotal agents, thereby disregarding the complex interactions within a real-world economic system. Furthermore, we pay attention to the vital role of the government policy in distributing tax credits. Instead of uniform distribution considered in state-of-the-art, it requires a well-designed strategy to reduce disparities among households and improve social welfare. To address these limitations, we propose an expansive multi-agent economic model comprising reinforcement learning agents of numerous types. Additionally, our research comprehensively explores the impact of tax credit allocation on household behavior and captures the spectrum of spending patterns that can be observed across diverse households. Further, we propose an innovative government policy to distribute tax credits, strategically leveraging insights from tax credit spending patterns. Simulation results illustrate the efficacy of the proposed government strategy in ameliorating inequalities across households.

Control Barrier Functions (CBF) have provided a very versatile framework for the synthesis of safe control architectures for a wide class of nonlinear dynamical systems. Typically, CBF-based synthesis approaches apply to systems that exhibit nonlinear -- but smooth -- relationship in the state of the system and linear relationship in the control input. In contrast, the problem of safe control synthesis using CBF for hybrid dynamical systems, i.e., systems which have a discontinuous relationship in the system state, remains largely unexplored. In this work, we build upon the progress on CBF-based control to formulate a theory for safe control synthesis for hybrid dynamical systems. Under the assumption that local CBFs can be synthesized for each mode of operation of the hybrid system, we show how to construct CBF that can guarantee safe switching between modes. The end result is a switching CBF-based controller which provides global safety guarantees. The effectiveness of our proposed approach is demonstrated on two simulation studies.

In the realm of artificial intelligence and card games, this study introduces a two-step reinforcement learning (RL) strategy tailored for "The Lord of the Rings: The Card Game (LOTRCG)," a complex multistage strategy card game. This research diverges from conventional RL methods by adopting a phased learning approach, beginning with a foundational learning stage in a simplified version of the game and subsequently progressing to the complete, intricate game environment. This methodology notably enhances the AI agent's adaptability and performance in the face of LOTRCG's unpredictable and challenging nature. The paper also explores a multi-agent system, where distinct RL agents are employed for various decision-making aspects of the game. This approach has demonstrated a remarkable improvement in game outcomes, with the RL agents achieving a winrate of 78.5% across a set of 10,000 random games.

Recent advances in Competitive Self-Play (CSP) have achieved, or even surpassed, human level performance in complex game environments such as Dota 2 and StarCraft II using Distributed Multi-Agent Reinforcement Learning (MARL). One core component of these methods relies on creating a pool of learning agents -- consisting of the Main Agent, past versions of this agent, and Exploiter Agents -- where Exploiter Agents learn counter-strategies to the Main Agents. A key drawback of these approaches is the large computational cost and physical time that is required to train the system, making them impractical to deploy in highly iterative real-life settings such as video game productions. In this paper, we propose the Minimax Exploiter, a game theoretic approach to exploiting Main Agents that leverages knowledge of its opponents, leading to significant increases in data efficiency. We validate our approach in a diversity of settings, including simple turn based games, the arcade learning environment, and For Honor, a modern video game. The Minimax Exploiter consistently outperforms strong baselines, demonstrating improved stability and data efficiency, leading to a robust CSP-MARL method that is both flexible and easy to deploy.

The concept of rationality is central to the field of artificial intelligence. Whether we are seeking to simulate human reasoning, or the goal is to achieve bounded optimality, we generally seek to make artificial agents as rational as possible. Despite the centrality of the concept within AI, there is no unified definition of what constitutes a rational agent. This article provides a survey of rationality and irrationality in artificial intelligence, and sets out the open questions in this area. The understanding of rationality in other fields has influenced its conception within artificial intelligence, in particular work in economics, philosophy and psychology. Focusing on the behaviour of artificial agents, we consider irrational behaviours that can prove to be optimal in certain scenarios. Some methods have been developed to deal with irrational agents, both in terms of identification and interaction, however work in this area remains limited. Methods that have up to now been developed for other purposes, namely adversarial scenarios, may be adapted to suit interactions with artificial agents. We further discuss the interplay between human and artificial agents, and the role that rationality plays within this interaction; many questions remain in this area, relating to potentially irrational behaviour of both humans and artificial agents.

We study the problem of building a controller that can follow open-ended instructions in open-world environments. We propose to follow reference videos as instructions, which offer expressive goal specifications while eliminating the need for expensive text-gameplay annotations. A new learning framework is derived to allow learning such instruction-following controllers from gameplay videos while producing a video instruction encoder that induces a structured goal space. We implement our agent GROOT in a simple yet effective encoder-decoder architecture based on causal transformers. We evaluate GROOT against open-world counterparts and human players on a proposed Minecraft SkillForge benchmark. The Elo ratings clearly show that GROOT is closing the human-machine gap as well as exhibiting a 70% winning rate over the best generalist agent baseline. Qualitative analysis of the induced goal space further demonstrates some interesting emergent properties, including the goal composition and complex gameplay behavior synthesis. The project page is available at https://craftjarvis-groot.github.io.

Autonomous Vehicles (AVs) promise a range of societal advantages, including broader access to mobility, reduced road accidents, and enhanced transportation efficiency. However, evaluating the risks linked to AVs is complex due to limited historical data and the swift progression of technology. This paper presents a data-driven framework for assessing the risk of different AVs' behaviors in various operational design domains (ODDs), based on counterfactual simulations of "misbehaving" road users. We propose the notion of counterfactual safety margin, which represents the minimum deviation from nominal behavior that could cause a collision. This methodology not only pinpoints the most critical scenarios but also quantifies the (relative) risk's frequency and severity concerning AVs. Importantly, we show that our approach is applicable even when the AV's behavioral policy remains undisclosed, through worst- and best-case analyses, benefiting external entities like regulators and risk evaluators. Our experimental outcomes demonstrate the correlation between the safety margin, the quality of the driving policy, and the ODD, shedding light on the relative risks of different AV providers. Overall, this work contributes to the safety assessment of AVs and addresses legislative and insurance concerns surrounding this burgeoning technology.

We introduce and study pawn games, a class of two-player zero-sum turn-based graph games. A turn-based graph game proceeds by placing a token on an initial vertex, and whoever controls the vertex on which the token is located, chooses its next location. This leads to a path in the graph, which determines the winner. Traditionally, the control of vertices is predetermined and fixed. The novelty of pawn games is that control of vertices changes dynamically throughout the game as follows. Each vertex of a pawn game is owned by a pawn. In each turn, the pawns are partitioned between the two players, and the player who controls the pawn that owns the vertex on which the token is located, chooses the next location of the token. Control of pawns changes dynamically throughout the game according to a fixed mechanism. Specifically, we define several grabbing-based mechanisms in which control of at most one pawn transfers at the end of each turn. We study the complexity of solving pawn games, where we focus on reachability objectives and parameterize the problem by the mechanism that is being used and by restrictions on pawn ownership of vertices. On the positive side, even though pawn games are exponentially-succinct turn-based games, we identify several natural classes that can be solved in PTIME. On the negative side, we identify several EXPTIME-complete classes, where our hardness proofs are based on a new class of games called Lock & Key games, which may be of independent interest.