Learning Dynamic Abstract Representations for Sample-Efficient Reinforcement Learning

no code implementations • 4 Oct 2022 • Mehdi Dadvar, Rashmeet Kaur Nayyar, Siddharth Srivastava

In many real-world problems, the learning agent needs to learn a problem's abstractions and solution simultaneously.

reinforcement-learning Reinforcement Learning (RL)

Multi-Agent Task Allocation in Complementary Teams: A Hunter and Gatherer Approach

no code implementations • 12 Dec 2019 • Mehdi Dadvar, Saeed Moazami, Harley R. Myler, Hassan Zargarzadeh

Consider a dynamic task allocation problem, where tasks are unknowingly distributed over an environment.

Decision Making

Exploration and Coordination of Complementary Multi-Robot Teams in a Hunter and Gatherer Scenario

no code implementations • 12 Dec 2019 • Mehdi Dadvar, Saeed Moazami, Harley R. Myler, Hassan Zargarzadeh

Besides, we present a coordination solution between hunters and gatherers by integrating the novel notion of profit margins into the concept of expected information gain.