Accepted author manuscript, 585 KB, PDF document
Final published version
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Towards Large Scale Ad-hoc Teamwork
AU - Shafipour Yourdshahi, Elnaz
AU - Pinder, Thomas
AU - Dhawan, Gauri
AU - Soriano Marcolino, Leandro
AU - Angelov, Plamen Parvanov
PY - 2018/9/13
Y1 - 2018/9/13
N2 - 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 compact 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 ad-hoc 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 problern for ad-hoc teamwork.
AB - 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 compact 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 ad-hoc 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 problern for ad-hoc teamwork.
U2 - 10.1109/AGENTS.2018.8460136
DO - 10.1109/AGENTS.2018.8460136
M3 - Conference contribution/Paper
BT - 2018 IEEE International Conference on Agents (ICA)
PB - IEEE
ER -