Learning from demonstration (LfD) has been emerged as a successful transfer learning technique to speed up reinforcement learning (RL). However, the effectiveness of the LfD heavily depends on the quality of the demonstrations. This work investigates ...

Electronic marketplaces and the automation of trading have transformed the financial market from a human-decision ecosystem to an algorithmic one. Questions and challenges that arise from this new algorithmic ecosystem naturally lend themselves to ...

Reinforcement learning methods have successfully been applied to build autonomous agents that solve challenging sequential decision-making problems. However, agents need a long time to learn a task, especially when multiple autonomous agents are in the ...

My research area is interdisciplinary to Mechanism Design and Algorithm Design. The problems I find interesting in Computational Mechanism Design are Voting preferences, Environment protection by reducing the emission of harmful gases from automobiles, ...

We present here work on two types of matching problems, namely Hedonic Games, also known as Coalition Formation Games, and on quota-based lottery systems such as the one used in Singapore to allocate public housing. We introduce two Hedonic Games, and ...

Mechanism design is the task to design algorithms, toward desired objectives, that is robust to potential manipulation by strategic players. Traditionally, it is assumed that the mechanism designer and the players in the economy share some common ...

Complex information systems operate with increasing degrees of autonomy. Consequently, such systems should not only optimize for simple metrics (like clicks and views) that reflect the system provider's preferences but also consider norms or rules, as ...

Shared ownership of computing resources has long been in the practice; here, multiple agents pool their resources together to achieve high utility and low wastefulness. Sharing incentive, non-wastefulness and strategyproofness are three of the most ...

Our research investigates the influence of distances on elections and the associated problems such as bribery, manipulation, and control. Distances can be used in elections in many different ways. In the case of interference problems, distances can be ...

While achieving the state-of-the-art performance in complex sequential tasks, deep reinforcement learning (deep RL) remains extremely data inefficient. Many approaches have been studied to improve the data efficiency of deep RL algorithms. This ...

The use of multi-robot teams for field missions is increasing in number and scope, requiring command and control interfaces to be adapted to the operator's needs. Instead of working on interaction modalities that emerge from the engineering realm (...

This paper presents a new multi-agent decision support system with the purpose of aiding bilateral contract negotiators in the pre-negotiation phase, through the analysis of their possible opponents. The application area of this system is the ...

We present an experimental tool for verification of strategic abilities under imperfect information, as well as strategy synthesis. The problem is well known to be hard, both theoretically and in practice. The tool, called StraTegic Verifier (STV), ...

Continuous matching of supply and demand through online/real-time decision making is a problem of critical importance in many urban environments. Examples include bike/scooter sharing systems, car sharing, food/ grocery delivery, smart vending machines ...

Real-world transportation networks provide rich and complex environments, well-suited to the deployment of multi-agent systems. In this demonstration, we simulate a population of electric vehicles making a journey between two cities. The challenge for ...

For The Record is a digital game that involves a social dilemma between a mixed team of humans and agents. Inspired by the standard public goods games, the collective goal is accessible to all team members, independently of their individual ...

This demonstration highlights the design of the CONSULT system, a modular decision-support system (DSS) intended to help patients suffering from chronic conditions self-manage their treatments. The system takes input from multiple sources, including ...

We train a neural network to control a drumstick fastened to a motor. The network takes a temporally arranged sequence of desired strikes, or a rhythm, as input and outputs a sequence of motor velocities controlling the drumstick's physical movement. We ...

By using a multiagent reinforcement learning (MARL) framework, cooperative agents can communicate with one another to accelerate the joint learning. In the teacher-student paradigm applied in MARL, a more experienced agent (advisor) can advise another ...

Recent advances in deep reinforcement learning have achieved human-level performance on a variety of real-world applications. However, the current algorithms still suffer from poor gradient estimation with excessive variance, resulting in unstable ...