Post-doc position on distributed multi-agent reinforcement learning.

The Data Mining and Machine Learning group, http://dmml.ch/, at the University of Applied Sciences in Geneva has an opening for a full-time post-doc position funded by the Swiss confederation in the context of an Horizon Europe collaborative project; funding is available for up to three years. Within the project the DMML group will develop distributed multi-agent reinforcement learning methods for collaborative decision making [1,2]. We are looking to develop approaches that scale well with the number of decision making agents, following consensus matching approaches [5,6], and learn how agents should communicate [3,4], i.e. with whom and when they should exchange information. The developed methods will be eventually deployed for distributed resource management on network continuum (IoT, Edge, Cloud). 

We seek strongly motivated candidates dedicated to high quality research. Candidates should have (or be close to obtaining) a Phd in machine learning, ideally in the area of generative modelling, and a strong research track-record attested by high quality publications in relevant machine learning venues such as ICML, NeurIPS, ICLR, AI-STATS, UAI, etc. The selected candidate is expected to demonstrate a high degree of independence and autonomy, drive their own research and actively contribute to the scientific development of the group through their knowledge and expertise as well as by proposing and contributing to group activities such as readings, schools, workshops etc. They are expected to participate in the supervision of PhD students. 

The DMML group consists of roughly a dozen of researchers at the PhD and Post-doc level, working in different areas of machine learning, such as generative models, reinforcement and imitation learning. The team collaborates closely with the VIPER group, https://viper.unige.ch, from the computer science department of the University of Geneva headed by Prof. Stephane Marchand-Maillet. We offer ample opportunities and support for scientific development, e.g. providing funding for conferences, schools, research visits and exchanges etc. We strive to provide a research environment in which researchers can focus on their research and allow for space and time to develop solid ideas.  

If interested, please send the following to [email protected] (subject: Post-Doc application, Hyper-AI Project)

- academic CV (max 2 pages)

- pointers to their two most important publications

- one page motivation letter explaining why the candidate is suitable for the position and what they can bring to the DMML group 

- 1000 word research proposal on the research topics described above 

- contact details of three referees (do not send reference letters)

- copies of diplomas (PhD, MSc, BSc) and academic transcripts  

Deadline for applications: 29/02/2024, starting date May 2024, negotiable. 

The announcement can also be found in the group web page http://dmml.ch/recruitment/ 

In case of any further questions, please contact [email protected].

[1] Oriol Vinyals et al. “Grandmaster level in StarCraft II using multi-agent reinforcement learning”. In: Nature (2019), pp. 1–5.

[2] Pablo Hernandez-Leal, Bilal Kartal, and Matthew E. Taylor. “A survey and critique of multiagent deep reinforcement learning”. In: Autonomous Agents and Multi-Agent Systems 33 (2019)

[3] Sergio Valcarcel Macua et al. “Diff-DAC: Distributed Actor-Critic for Average Multitask Deep Reinforcement Learning”. In: Adaptive Learning Agents (ALA) Conference. 2018.

[4] L. Cassano, K. Yuan, and A. H. Sayed. “Multiagent Fully Decentralized Value Function Learning With Linear Convergence Rates”. In: IEEE Transactions on Automatic Control 66.4 (2021)

[5] Kyunghwan Son et al. “QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning”. In: Proceedings of the 36th International Conference on Machine Learning, ICML

2019, 9-15 June 2019, Long Beach, California, USA. Vol. 97. Proceedings of Machine Learning Research. PMLR, 2019.

[6] Peter Sunehag et al. “Value-decomposition networks for cooperative multiagent learning based on team reward”. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems. International Foundation for Autonomous Agents and Multiagent Systems.  2018.