Posts by Collection

portfolio

publications

Feasible Reachable Policy Iteration

Published in The 41st International Conference on Machine Learning (ICML 2024), 2024

FRPI is an efficient policy space pruning algorithm of safe reinforcement learning for goal-reaching problems with safety constraints, which achieves the best performance both in safety and return.

Recommended citation: @inproceedings{qinfeasible, title={Feasible Reachable Policy Iteration}, author={Qin, Shentao and Yang, Yujie and Mu, Yao and Li, Jie and Zou, Wenjun and Li, Shengbo Eben and Duan, Jingliang}, booktitle={Forty-first International Conference on Machine Learning}, year={2024}, url={https://openreview.net/pdf?id=ks8qSwkkuZ} }
Download Slides

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.