Neural Information Processing Systems http://nips.cc/

Multi-agent multi-objective systems (MAMOS) have emerged as powerful frameworks for modelling complex decision-making problems across various real-world domains, such as robotic exploration, autonomous traffic management, and sensor network optimisation. MAMOS offers enhanced scalability and robustness through decentralised control and more accurately reflects inherent trade-offs between conflicting objectives. In MAMOS, each agent uses utility functions that map return vectors to scalar values. Existing MAMOS optimisation methods face challenges in handling heterogeneous objective and utility function settings, where training non-stationarity is intensified due to private utility functions and the associated policies. In this paper, we first theoretically prove that direct access to, or structured modeling of, global utility functions is necessary for the Bayesian Nash Equilibrium under decentralised execution constraints. To access the global utility functions while preserving the decentralised execution, we propose an Agent-Attention Multi-Agent Multi-Objective Reinforcement Learning (AA-MAMORL) framework. Our approach implicitly learns a joint belief over other agents' utility functions and their associated policies during centralised training, effectively mapping global states and utilities to each agent's policy. In execution, each agent independently selects actions based on local observations and its private utility function to approximate a BNE, without relying on inter-agent communication. We conduct comprehensive experiments in both a custom-designed MAMO Particle environment and the standard MOMALand benchmark. The results demonstrate that access to global preferences and our proposed AA-MAMORL significantly improve performance and consistently outperform state-of-the-art methods.

Ensemble learning is a standard approach to building machine learning systems that capture complex phenomena in real-world data. An important aspect of these systems is the complete and valid quantification of model uncertainty.

Large public gatherings or crowds are commonplace and have been the subject of simulation research in many studies related to crowd management, disaster management and evacuation planning (Babojelić and Novacko 2020). However, in-depth research on pedestrians has been hindered by difficulties such as complex individual behaviours, different disaster characteristics, and varying environmental factors (Wijermans and Templeton 2022). As evacuee behaviour and movement vary in different scenarios, a number of field observations and simulation experiments have been conducted to explore pedestrian flows, movement patterns and potential factors affecting evacuation under different types of emergencies (Rozo et al. 2019; Feng et al. 2021; Sevtsuk and Kalvo 2022). Despite many simulation studies of pedestrian behaviours, few common behavioural features of pedestrian flows have been explored (Vermuyten et al. 2016; Babojelić and Novacko 2020). One of the main obstacles is the lack of experimental datasets that closely match individual movements during evacuations in the real world.

While the complexity of computing Bayes-Nash equilibria Applications of combinatorial auctions (CA) as market mechanisms (BNE) is not well understood, Cai and Papadimitriou [14] show that are prevalent in practice, yet their Bayesian Nash equilibria (BNE) BNE computation for a specific combinatorial auction is already (at remain poorly understood. Analytical solutions are known only for least) PP-hard. Furthermore, finding an -approximation to a BNE is a few cases where the problem can be reformulated as a tractable still NP-hard. Explicit solutions exist for very few specific environments, partial differential equation (PDE). In the general case, finding BNE but in general, we neither know whether a BNE exists nor is known to be computationally hard. Previous work on numerical do we have a solution theory. Combinatorial auctions have become computation of BNE in auctions has relied either on solving such a pivotal research problem in algorithmic game theory [29] and PDEs explicitly, calculating pointwise best-responses in strategy they are widely used in the field [8, 15]. Thus, understanding their space, or iteratively solving restricted subgames. In this study, we equilibria is paramount, and access to scalable numerical methods present a generic yet scalable alternative multi-agent equilibrium for computing or approximating BNE can have a significant impact.

Ensemble learning is a standard approach to building machine learning systems that capture complex phenomena in real-world data. An important aspect of these systems is the complete and valid quantification of model uncertainty. We introduce a Bayesian nonparametric ensemble (BNE) approach that augments an existing ensemble model to account for different sources of model uncertainty. BNE augments a model's prediction and distribution functions using Bayesian nonparametric machinery. It has a theoretical guarantee in that it robustly estimates the uncertainty patterns in the data distribution, and can decompose its overall predictive uncertainty into distinct components that are due to different sources of noise and error. We show that our method achieves accurate uncertainty estimates under complex observational noise, and illustrate its real-world utility in terms of uncertainty decomposition and model bias detection for an ensemble in predict air pollution exposures in Eastern Massachusetts, USA.

Have you ever felt you are losing too much time in traffic? Have you ever asked why all the cars on the roads can't just all go with some constant speed? Most drivers have had such thoughts. And if you live in a large city, you may relate to this funny scene from "Office Space": In this post, we will present a mathematical model of traffic congestion and explain why it happens using this model. Afterwards, we will analyze the effects of a recently emerging and popular technology, autonomous cars, on traffic congestion. As we showed in our WAFR 2018 paper, "Altruistic Autonomy: Beating Congestion on Shared Roads", autonomous cars have the potential of significantly reducing traffic congestion!

The Condorcet Jury Theorem justifies the wisdom of crowds and lays the foundations of the ideology of the democratic regime. However, the Jury Theorem and most of its extensions focus on two alternatives and none of them quantitatively evaluate the effect of agents’ strategic behavior on the mechanism’s truth-revealing power. We initiate a research agenda of quantitatively extend- ing the Jury Theorem with strategic agents by characterizing the price of anarchy (PoA) and the price of stability (PoS) of the common interest Bayesian voting games for three classes of mechanisms: plurality, MAPs, and the mechanisms that satisfy anonymity, neutrality, and strategy-proofness (w.r.t. a set of natural probabil- ity models). We show that while plurality and MAPs have better best-case truth-revealing power (lower PoS), the third class of mechanisms are more robust against agents’ strategic behavior (lower PoA).