There are a few news items to share from the lab this month.
AAMAS 2023 Conference
Next week Sriram will be in London for the AAMAS 2023 conference where he’s presenting his paper “Learning from Multiple Independent Advisors in Multi-agent Reinforcement Learning” (Ganapathi Subramanian et al., 2023) which looks at the problem of simultaneously learning from multiple independent advisors in a multi-agent reinforcement learning setting. The approach leverages a two-level Q-learning architecture extended to multi-agent settings and includes algorithms for incorporating a set of advisors by both evaluating the advisors at each state and subsequently using the advisors to guide action selection. There are also great theoretical convergence and sample complexity guarantees as well as empirical validation through simulation experiments.
PhD Thesis Award for Sriram!
Every year the Canadian Society for the Computational Studies of Intelligence (or Société Canadienne pour l’étude de l’intelligence par ordinateur)(CAIAC) calls out for nominations for the best PhD dissertation in Canada on the topic of Artificial Intelligence. Supervisors and Department Chairs nominate graduates from the previous year, then the thesis and support letters are evaluated by an independent committee of Professors from across Canada. This year, our lab’s most recent PhD graduate, Sriram Ganapathi Subramanian, has been chosen for the best dissertation (Subramanian, 2022). It’s a huge honour and we’re all very proud of him, congratulations Sriram!
Sriram will give an acceptance talk on his thesis research at the Canadian AI 2023 conference this year in Montreal at McGill.
Sriram is currently a postdoc position at the Vector Institute working with Prof. Sheila Mcllraith at UofT and Prof. Pascal Poupart at UWaterloo.
ChemGymRL Arxiv Paper is Up
Related to our ongoing NRC funded project on Digital Chemistry and Material Design we have recently posted a paper preprint on Arxiv titled “ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry” (missing reference). The paper is a detailed introduction to the open-source simulation framework and experimental results on standard RL algorithms.
- Multi-Advisor-MARLLearning from Multiple Independent Advisors in Multi-agent Reinforcement LearningIn Proceedings of the 22nd International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), London, United Kingdom. Sep, 2023.
- Phd ThesisMulti-Agent Reinforcement Learning in Large Complex EnvironmentsUWSpace, Jun, 2022.