Towards Large Scale Ad-hoc Teamwork

Elnaz Shafipour Yourdshahi, Thomas Pinder, Gauri Dhawan, Leandro Soriano Marcolino, Plamen Angelov
2018 2018 IEEE International Conference on Agents (ICA)  
In complex environments, agents must be able to cooperate with previously unknown team-mates, and hence dynamically learn about other agents in the environment while searching for optimal actions. Previous works employ Monte Carlo Tree Search approaches. However, the search tree increases exponentially with the number of agents, and only scenarios with very small team sizes have been explored. Hence, in this paper we propose a history-based version of UCT Monte Carlo Tree Search, using a more
more » ... mpact representation than the original algorithm. We perform several experiments with a varying number of agents in the level-based foraging domain, an important testbed for adhoc teamwork. We achieve better overall performance than the state-of-the-art and better scalability with team size. Additionally, we contribute an open-source version of our system, making it easier for the research community to use the level-based foraging domain as a benchmark problem for ad-hoc teamwork.
doi:10.1109/agents.2018.8460136 fatcat:i6dtyyprn5cmbisdqlhrk35cx4