We study a heterogeneous agent macroeconomic model with an infinite number of households and firms competing in a labor market. Each household earns income and engages in consumption at each time step while aiming to maximize a concave utility subject to the underlying market conditions. The households aim to find the optimal saving strategy that maximizes their discounted cumulative utility given the market condition, while the firms determine the market conditions through maximizing corporate profit based on the household population behavior. The model captures a wide range of applications in macroeconomic studies, and we propose a data-driven reinforcement learning framework that finds the regularized competitive equilibrium of the model. The proposed algorithm enjoys theoretical guarantees in converging to the equilibrium of the market at a sub-linear rate.

One of the widely used peak reduction methods in smart grids is demand response, where one analyzes the shift in customers' (agents') usage patterns in response to the signal from the distribution company. Often, these signals are in the form of incentives offered to agents. This work studies the effect of incentives on the probabilities of accepting such offers in a real-world smart grid simulator, PowerTAC. We first show that there exists a function that depicts the probability of an agent reducing its load as a function of the discounts offered to them. We call it reduction probability (RP). RP function is further parametrized by the rate of reduction (RR), which can differ for each agent. We provide an optimal algorithm, MJS--ExpResponse, that outputs the discounts to each agent by maximizing the expected reduction under a budget constraint. When RRs are unknown, we propose a Multi-Armed Bandit (MAB) based online algorithm, namely MJSUCB--ExpResponse, to learn RRs. Experimentally we show that it exhibits sublinear regret. Finally, we showcase the efficacy of the proposed algorithm in mitigating demand peaks in a real-world smart grid system using the PowerTAC simulator as a test bed.

Recent work in the multi-agent domain has shown the promise of Graph Neural Networks (GNNs) to learn complex coordination strategies. However, most current approaches use minor variants of a Graph Convolutional Network (GCN), which applies a convolution to the communication graph formed by the multi-agent system. In this paper, we investigate whether the performance and generalization of GCNs can be improved upon. We introduce ModGNN, a decentralized framework which serves as a generalization of GCNs, providing more flexibility. To test our hypothesis, we evaluate an implementation of ModGNN against several baselines in the multi-agent flocking problem. We perform an ablation analysis to show that the most important component of our framework is one that does not exist in a GCN. By varying the number of agents, we also demonstrate that an application-agnostic implementation of ModGNN possesses an improved ability to generalize to new environments.

Responsibility attribution is a key concept of accountable multi-agent decision making. Given a sequence of actions, responsibility attribution mechanisms quantify the impact of each participating agent to the final outcome. One such popular mechanism is based on actual causality, and it assigns (causal) responsibility based on the actions that were found to be pivotal for the considered outcome. However, the inherent problem of pinpointing actual causes and consequently determining the exact responsibility assignment has shown to be computationally intractable. In this paper, we aim to provide a practical algorithmic solution to the problem of responsibility attribution under a computational budget. We first formalize the problem in the framework of Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) augmented by a specific class of Structural Causal Models (SCMs). Under this framework, we introduce a Monte Carlo Tree Search (MCTS) type of method which efficiently approximates the agents' degrees of responsibility. This method utilizes the structure of a novel search tree and a pruning technique, both tailored to the problem of responsibility attribution. Other novel components of our method are (a) a child selection policy based on linear scalarization and (b) a backpropagation procedure that accounts for a minimality condition that is typically used to define actual causality. We experimentally evaluate the efficacy of our algorithm through a simulation-based test-bed, which includes three team-based card games.

It plays a central role in intelligent agent systems to model agent's epistemic state and its change. Asynchrony plays a key role in distributed systems, in which the messages transmitted may not be received instantly by the agents. To characterize asynchronous communications, asynchronous announcement logic (AAL) has been presented, which focuses on the logic laws of the change of epistemic state after receiving information. However AAL does not involve the interactive behaviours between an agent and its environment. Through enriching the well-known pi-calculus by adding the operators for passing basic facts and applying the well-known action model logic to describe agents' epistemic states, this paper presents the e-calculus to model epistemic interactions between agents with epistemic states. The e-calculus can be adopted to characterize synchronous and asynchronous communications between agents. To capture the asynchrony, a buffer pools is constructed to store the basic facts announced and each agent reads these facts from this buffer pool in some order. Based on the transmission of link names, the e-calculus is able to realize reading from this buffer pool in different orders. This paper gives two examples: one is to read in the order in which the announced basic facts are sent (First-in-first-out, FIFO), and the other is in an arbitrary order.

In representative democracies, the election of new representatives in regular election cycles is meant to prevent corruption and other misbehavior by elected officials and to keep them accountable in service of the ``will of the people." This democratic ideal can be undermined when candidates are dishonest when campaigning for election over these multiple cycles or rounds of voting. Much of the work on COMSOC to date has investigated strategic actions in only a single round. We introduce a novel formal model of \emph{pandering}, or strategic preference reporting by candidates seeking to be elected, and examine the resilience of two democratic voting systems to pandering within a single round and across multiple rounds. The two voting systems we compare are Representative Democracy (RD) and Flexible Representative Democracy (FRD). For each voting system, our analysis centers on the types of strategies candidates employ and how voters update their views of candidates based on how the candidates have pandered in the past. We provide theoretical results on the complexity of pandering in our setting for a single cycle, formulate our problem for multiple cycles as a Markov Decision Process, and use reinforcement learning to study the effects of pandering by both single candidates and groups of candidates across a number of rounds.

Building open-ended agents that can autonomously discover a diversity of behaviours is one of the long-standing goals of artificial intelligence. This challenge can be studied in the framework of autotelic RL agents, i.e. agents that learn by selecting and pursuing their own goals, self-organizing a learning curriculum. Recent work identified language as a key dimension of autotelic learning, in particular because it enables abstract goal sampling and guidance from social peers for hindsight relabelling. Within this perspective, we study the following open scientific questions: What is the impact of hindsight feedback from a social peer (e.g. selective vs. exhaustive)? How can the agent learn from very rare language goal examples in its experience replay? How can multiple forms of exploration be combined, and take advantage of easier goals as stepping stones to reach harder ones? To address these questions, we use ScienceWorld, a textual environment with rich abstract and combinatorial physics. We show the importance of selectivity from the social peer's feedback; that experience replay needs to over-sample examples of rare goals; and that following self-generated goal sequences where the agent's competence is intermediate leads to significant improvements in final performance.

Counterfactual explanations are a common tool to explain artificial intelligence models. For Reinforcement Learning (RL) agents, they answer "Why not?" or "What if?" questions by illustrating what minimal change to a state is needed such that an agent chooses a different action. Generating counterfactual explanations for RL agents with visual input is especially challenging because of their large state spaces and because their decisions are part of an overarching policy, which includes long-term decision-making. However, research focusing on counterfactual explanations, specifically for RL agents with visual input, is scarce and does not go beyond identifying defective agents. It is unclear whether counterfactual explanations are still helpful for more complex tasks like analyzing the learned strategies of different agents or choosing a fitting agent for a specific task. We propose a novel but simple method to generate counterfactual explanations for RL agents by formulating the problem as a domain transfer problem which allows the use of adversarial learning techniques like StarGAN. Our method is fully model-agnostic and we demonstrate that it outperforms the only previous method in several computational metrics. Furthermore, we show in a user study that our method performs best when analyzing which strategies different agents pursue.

In domains where agents interact strategically, game theory is applied widely to predict how agents would behave. However, game-theoretic predictions are based on the assumption that agents are fully rational and believe in equilibrium plays, which unfortunately are mostly not true when human decision makers are involved. To address this limitation, a number of behavioral game-theoretic models are defined to account for the limited rationality of human decision makers. The "quantal cognitive hierarchy" (QCH) model, which is one of the more recent models, is demonstrated to be the state-of-art model for predicting human behaviors in normal-form games. The QCH model assumes that agents in games can be both non-strategic (level-0) and strategic (level-$k$). For level-0 agents, they choose their strategies irrespective of other agents. For level-$k$ agents, they assume that other agents would be behaving at levels less than $k$ and best respond against them. However, an important assumption of the QCH model is that the distribution of agents' levels follows a Poisson distribution. In this paper, we relax this assumption and design a learning-based method at the population level to iteratively estimate the empirical distribution of agents' reasoning levels. By using a real-world dataset from the Swedish lowest unique positive integer game, we demonstrate how our refined QCH model and the iterative solution-seeking process can be used in providing a more accurate behavioral model for agents. This leads to better performance in fitting the real data and allows us to track an agent's progress in learning to play strategically over multiple rounds.

The problem of permutation-invariant learning over set representations is particularly relevant in the field of multi-agent systems -- a few potential applications include unsupervised training of aggregation functions in graph neural networks (GNNs), neural cellular automata on graphs, and prediction of scenes with multiple objects. Yet existing approaches to set encoding and decoding tasks present a host of issues, including non-permutation-invariance, fixed-length outputs, reliance on iterative methods, non-deterministic outputs, computationally expensive loss functions, and poor reconstruction accuracy. In this paper we introduce a Permutation-Invariant Set Autoencoder (PISA), which tackles these problems and produces encodings with significantly lower reconstruction error than existing baselines. PISA also provides other desirable properties, including a similarity-preserving latent space, and the ability to insert or remove elements from the encoding. After evaluating PISA against baseline methods, we demonstrate its usefulness in a multi-agent application. Using PISA as a subcomponent, we introduce a novel GNN architecture which serves as a generalised communication scheme, allowing agents to use communication to gain full observability of a system.