Postdoctoral Researcher
Facebook AI Research
PhD '19 Georgia Institute of Technology
Areas of Interest
- Artificial Intelligence
Poster
Exploring Emergent Communication in Embodied Multi-Agent Populations
Abstract
Effective communication is an important skill for enabling information exchange and cooperation in multi-agent settings. Indeed, emergent communication is now a vibrant field of research, with common settings involving discrete cheap-talk channels. One limitation of this setting is that it does not allow for the emergent protocols to generalize beyond the training partners. Furthermore, so far emergent communication has primarily focused on the use of symbolic channels (via discrete symbols, e.g. words). In this work, we extend this line of work to a new modality, by studying agents that learn to communicate via actuating their joints in a 3D simulated environment. We show that under realistic assumptions, a non-uniform distribution over intents and a common-knowledge energy cost, agents can learn communication protocols that generalize to novel partners. We also explore and analyze specific difficulties associated with finding globally optimal solutions in practice. Finally, we propose and evaluate initial training improvements to address these challenges, involving both specific training curricula and providing the latent features that can be coordinated upon during training.
Bio
Kalesha Bullard is a postdoctoral researcher at Facebook AI Research. She completed her PhD in Computer Science at Georgia Institute of Technology in 2019, where her research lied at the intersection of human-robot interaction and machine learning, in interactive robot learning. During her postdoc, Kalesha has expanded her research to explore the space of multi-agent reinforcement learning, currently investigating how to enable embodied multi-agent populations to learn generalizable communication protocols. More broadly, Kalesha’s research interests span the space of autonomous reasoning and decision making for artificial agents in multi-agent settings. To date, her research has focused on models and algorithms for enabling agents to learn through interaction with other agents (human or artificial). Kalesha currently serves as a member of the organizing committee for the NeurIPS 2020 Workshop on Talking to Strangers: Zero-Shot Emergent Communication and on the program committee for the NeurIPS 2020 Cooperative AI Workshop. She previously served as a Program Committee (PC) member for the 2019 International Conference on Autonomous Agents and Multi-Agent Systems, PC Co-Chair for the 2018 Young Researcher's Roundtable on Spoken Dialogue Systems, and PC Co-Chair the 2017 AAAI Fall Symposium on Artificial Intelligence for Human-Robot Interaction. In addition, she has been an Area Chair for the NeurIPS Women in Machine Learning workshop since 2019.
