New Zealand

The goal of multi-objective problems is to find solutions that balance different objectives. When solving multi-objective problems using reinforcement learning linear scalarisation techniques are generally used, however system expertise is required to optimise the weights for linear scalarisation. Thresholded Lexicographic Ordering (TLO) is one technique that avoids the need for an expert to specify weights; instead a system designer can directly specify a preferred ordering over objectives, along with a desired threshold value for each objective. In this presentation we propose a novel algorithm to dynamically set thresholds for use with TLO. We also present the first evaluation of TLO in a complex multi-objective multi-agent problem, the Dynamic Economic Emissions Dispatch domain. Our empirical results demonstrate that TLO with our dynamic thresholding algorithm achieves superior results when compared with a hand-tuned linear scalarisation method from previously published work.

AAMAS 2020

Dynamic Thresholded Lexicographic Ordering

AAMAS is the largest and most influential conference in the area of agents and multiagent systems, bringing together researchers and practitioners in all areas of agent technology and providing and internationally renowned high-profile forum for publishing and finding out about the latest developments in the field. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).  

![](https://assets.underline.io/uploads/markdown_image/1/image/ce4604bd54468a006164d16e080204fb.jpg)

Please click on the button below to register for this event.

If you are registered and see this page please check the account email you are logged in with. It must be the same as for the registration.

If you still have trouble accessing the contact please contact support at aamas2021@underline.io 

AAMAS 2021

technical paper

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). The aim of the joint conference is to provide a single, high-profile, internationally-respected archival forum for scientific research in the theory and practice of autonomous agents and multi-agent systems.

Browse keynotes, discussions, panels and over 300 presentations.


AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). 

Online social networks are known to lack adequate multi-user privacy support. In this paper we present EXPRI, an agent architecture that aims to assist users in managing multi-user privacy conflicts. By considering the personal utility of sharing content and the individually preferred moral values of each user involved in the conflict, EXPRI identifies the best collaborative solution by applying practical reasoning techniques. Such techniques provide the agent with the cognitive process that is necessary for explainability. Furthermore, the knowledge gathered during the practical reasoning process allows EXPRI to engage in contrastive explanations.

Agent EXPRI: Licence to Explain

We propose a market-inspired bidding scheme for the assignment of paper reviews in large academic conferences. The primary contribution is an analysis of the incentives of reviewers during the bidding phases, when reviewers have private costs and some information about the demand for each paper, and want to obtain the best possible k papers for a predetermined k. We show that by assigning budgets to reviewers and a `price' for every paper that is (roughly) inversely proportional to its demand, the best response of a reviewer is to bid sincerely, i.e., on her most favorite papers, and match the budget even when it is not enforced. Finally, we show via extensive simulations on bidding data from real conferences, that our suggested bidding scheme would substantially improve the assignment, under several common assignment algorithms.

A Market-Inspired Bidding Scheme for Peer Review Paper Assignment

In the capacitated production planning problem, quantities of products need to be determined at consecutive periods within a given time horizon when product demands, costs, and production capacities vary through time. We focus on a general formulation of this problem where each product is produced in one step and setup cost is paid at each period of production. Additionally, products can be anticipated or backordered in respect to the demand period. We propose a computationally efficient decentralized approach based on the spillover effect relating to the accumulation of production costs of each product demand through time. The performance of the spillover algorithm is compared against the state-of-the-art mixed integer programming branch-and-bound solver CPLEX 12.8 considering optimality gap and computational time.

A Decentralized Multi-Agent Coordination Method for Dynamic and Constrained Production Planning

Reinforcement learning has been applied to numerous decision-making problems, but it requires careful specification of a reward function to represent the objective of the problem.
In many problems, it is difficult to represent the objective as a function, and thus it is easier to give expert demonstrations. Inverse reinforcement learning can be applied to such problems because it estimates the reward function from the expert's demonstrations.
Most existing inverse reinforcement learning methods assume that an expert gives demonstrations in a fixed environment, although the expert can provide demonstrations for a specific objective in multiple environments. For example, it is difficult to formulate a suitable reward function to represent driving a car, and the driver can give demonstrations in multiple situations. In such cases, normal practice is to use demonstrations in multiple environments to estimate the expert's reward. Herein, we formulate this problem based on a Bayesian inverse reinforcement learning framework and propose a mini-batch Markov chain Monte Carlo method. An advantage of our method is scalability. Our proposed method is scalable with respect to a number of environments in which expert demonstrations are generated. Experimental results show quantitatively that the proposed method outperforms existing inverse reinforcement learning methods.

Mini-batch Bayesian Inverse Reinforcement Learning for Multiple Dynamics

Levaraging Communication Topologies between Learning Agents in Deep Reinforcements Learning

Geographical clusters of undervaccinated populations have emerged in various parts of the United States in recent years. Public health response involves surveillance and field work, which is very resource-intensive. Given that public health resources are often limited, iden- tifying and rank-ordering critical clusters can help prioritize and allocate scarce resources for surveillance and quick intervention. We quantify the criticality of a cluster as the additional number of infections caused if the cluster is underimmunized. We focus on finding clusters that maximize this measure and develop efficient approximation algorithms for finding critical clusters by exploiting structural properties of the problem. Our methods involve solving a more general problem of maximizing a submodular function on a graph with connectivity constraints. We apply our methods to the state of Minnesota, where we find clusters with significantly higher criticality than those obtained by heuristics used in public health.

Finding Spatial Clusters Susceptible to Epidemic Outbreaks due to Undervaccination

Multi-agent Adversial Inverse Reinforcemetn Learning with Latent Variables

The Price of Anarchy of Self-Selection in Tullock Contests

Narrow the gap between distribution of task goals and virtual goals.

Hindsight Planner

Drawing an inspiration from behavioral studies of human decision making, we propose here a more general and flexible parametric framework for reinforcement learning that extends standard Q-learning to a two-stream model for processing positive and negative rewards, and allows to incorporate a wide range of reward-processing biases -- an important component of human decision making which can help us better understand a wide spectrum of multi-agent interactions in complex real-world socioeconomic systems, as well as various neuropsychiatric conditions associated with disruptions in normal reward processing. From the computational perspective, we observe that the proposed Split-QL model and its clinically inspired variants consistently outperform standard Q-Learning and SARSA methods, as well as recently proposed Double Q-Learning approaches, on simulated tasks with particular reward distributions, a real-world dataset capturing human decision-making in gambling tasks, and the Pac-Man game in a lifelong learning setting across different reward stationarities.

Dynamic Thresholded Lexicographic Ordering

Downloads

Next from AAMAS 2020

Agent EXPRI: Licence to Explain

Similar lecture

Mitigating Negative Side Effects via Environment Shaping

Dynamic Thresholded Lexicographic Ordering

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAMAS 2020

Agent EXPRI: Licence to Explain

Similar lecture

Mitigating Negative Side Effects via Environment Shaping

Downloads