Dr.
Flint Xiaofeng Fan
Distributed Computing Group
Computer Engineering and Networks Laboratory (TIK)
Department Electrical Engineering (D-ITET)
Office ETZ G 97
ETH Zurich
Gloriastrasse 35
8092 Zurich
Switzerland
Publications
-
Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs
Flint Xiaofeng Fan, Cheston Tan, Roger Wattenhofer and Yew-Soon Ong.
International Joint Conference on Neural Networks (IJCNN), Rome, Italy, July 2025.
External BibTeX -
FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF
Flint Xiaofeng Fan, Cheston Tan, Yew-Soon Ong, Roger Wattenhofer and Wei-Tsang Ooi.
24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Detroit, Michigan, USA, May 2025.
External Slides (PDF) BibTeX -
SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems
Nathan Corecco, Giorgio Piatti, Luca Lanzendörfer, Flint Xiaofeng Fan and Roger Wattenhofer.
27th European Conference on Artificial Intelligence (ECAI), Santiago de Compostela, Galicia, Spain, October 2024.
BibTeX -
Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence
Philip Jordan, Florian Grötschla, Flint Xiaofeng Fan and Roger Wattenhofer.
23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Auckland, New Zealand, May 2024.
External BibTeX -
CAESAR: Enhancing Federated RL in Heterogeneous MDPs through Convergence-Aware Sampling with Screening
Hei Yi Mak, Flint Xiaofeng Fan, Luca Lanzendörfer, Cheston Tan, Wei Tsang Ooi and Roger Wattenhofer.
The Sixteenth Workshop on Adaptive and Learning Agents (ALA@AAMAS), Auckland, New Zealand, May 2024.
External BibTeX -
Fault-tolerant federated reinforcement learning with theoretical guarantee
Flint Xiaofeng Fan, Yining Ma, Zhongxiang Dai, Wei Jing, Cheston Tan and Bryan Kian Hsiang Low.
Thirty-Fifth Annual Conference on Neural Information Processing Systems (NeurIPS), Online, December 2021.
External BibTeX
Theses & Labs
Available Theses & Labs | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Title | Type | Contact/Supervisor | Assigned | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 | Collective Decision-Making with Distributed LLMs | M/S | Flint Xiaofeng Fan | available | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 | Topics on Decentralized RLHF | M/S | Flint Xiaofeng Fan | available | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 | Topics on Distributed Reinforcement Learning | B/M/S | Flint Xiaofeng Fan | available | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Past Theses & Labs | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Title | Type | Contact/Supervisor | Assigned | Student(s) | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 | Federated Reinforcement Learning with Heterogeneous Environments [confidential] | S | Flint Xiaofeng Fan, Luca Lanzendörfer | FS 23 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 | SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems [confidential] | G | Flint Xiaofeng Fan, Luca Lanzendörfer | FS 23 | , | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 | Reinforcement Learning of TSP Heuristics with Message Passing Neural Networks | G | Flint Xiaofeng Fan, Joël Mathys | FS 23 | , | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 | Decentralized Federated Policy Gradient with Provably Fast Convergence and Byzantine Fault Tolerance [confidential] | S | Flint Xiaofeng Fan, Florian Grötschla | HS 22 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 | Reinforcement Learning for the Jass AI [confidential] | S | Benjamin Estermann, Flint Xiaofeng Fan | HS 22 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||