Stef Van Havermaet, Yara Khaluf, Pieter Simoens. No More Hand-Tuning Rewards: Masked Constrained Policy Optimization for Safe Reinforcement Learning. In Frank Dignum, Alessio Lomuscio, Ulle Endriss, Ann Nowé, editors, AAMAS '21: 20th International Conference on Autonomous Agents and Multiagent Systems, Virtual Event, United Kingdom, May 3-7, 2021. pages 1344-1352, ACM, 2021. [doi]
@inproceedings{HavermaetKS21,
title = {No More Hand-Tuning Rewards: Masked Constrained Policy Optimization for Safe Reinforcement Learning},
author = {Stef Van Havermaet and Yara Khaluf and Pieter Simoens},
year = {2021},
url = {https://dl.acm.org/doi/10.5555/3463952.3464107},
researchr = {https://researchr.org/publication/HavermaetKS21},
cites = {0},
citedby = {0},
pages = {1344-1352},
booktitle = {AAMAS '21: 20th International Conference on Autonomous Agents and Multiagent Systems, Virtual Event, United Kingdom, May 3-7, 2021},
editor = {Frank Dignum and Alessio Lomuscio and Ulle Endriss and Ann Nowé},
publisher = {ACM},
isbn = {978-1-4503-8307-3},
}