Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning
By Arrasy Rahman, Niklas Höpner, Filippos Christianos, Stefano V. Albrecht. 2020
79 citations recorded by the source corpus.
Ad hoc teamwork is the challenging problem of designing an autonomous agent which can adapt quickly to collaborate with teammates without prior coordination mechanisms, including joint training. Prior work in this area has focused on closed teams in which the number of agents is fixed. In this work, we consider open teams by allowing agents with different fixed policies to enter and leave the environment without prior notification. Our solution builds on graph neural networks to learn agent models and joint-action value models under varying team compositions. We contribute a novel action-value computation that integrates the agent model and joint-action value model to produce action-value estimates. We empirically demonstrate that our approach successfully models the effects other agents have on the learner, leading to policies that robustly adapt to dynamic team compositions and significantly outperform several alternative methods.
Subfields: Artificial Intelligence, Automotive Engineering, Computer Science Applications
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Filippos Christianos
- Georgios Papoudakis
- Stefano V. Albrecht
- Lukas Schäfer
- Arrasy Rahman
- Peter Stone
In Automotive Engineering
In Computer Science Applications
Citations in the corpus
- Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks (2020, methodology): “They have already been used in other multi-agent research [Christianos et al., 2020, 2021, Rahman et al., 2021, Papoudakis et al., 2021].”