Improving deep reinforcement learning by safety guarding model via hazardous experience planning

Graphical abstract

References

[1] Kai A , Deisenroth M P , Brundage M , Bharath A A . Deep reinforcement learning: a brief survey. IEEE Signal Processing Magazine, 2017, 34( 6): 26– 38

[2] Cheng R, Orosz G, Murray R M, Burdick J W. End-to-end safe reinforcement learning through barrier functions for safety-critical continuous control tasks. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2019, 3387−3395

[3] Saunders W, Sastry G, Stuhlmueller A, Evans O. Trial without error: towards safe reinforcement learning via human intervention. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems. 2018, 2067−2069

[4] Achiam J, Held D, Tamar A, Abbeel P. Constrained policy optimization. In: Proceedings of the International Conference on Machine Learning. 2017, 22– 31

[5] García J , Fernández F . A comprehensive survey on safe reinforcement learning. Journal of Machine Learning Research, 2015, 16 : 1437– 1480

[6] Chatzilygeroudis K , Vassiliades V , Mouret J B . Reset-free trial-and-error learning for robot damage recovery. Robotics and Autonomous Systems, 2018, 100 : 236– 250

[7] Zhu F , Wu W , Fu Y , Liu Q . A dual deep network based secure deep reinforcement learning method. Chinese Journal of Computers, 2019, 42( 8): 1812– 1826

Acknowledgements

This work was supported by the National Natural Science Foundation of China (Grant No. 61303108), Natural Science Foundation of Jiangsu Province (BK20211102), Suzhou Key Industries Technological Innovation-Prospective Applied Research Project (SYG201804); A Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions.

Supporting Information

The supporting information is available online at journal. hep. com. cn and link. springer. com

RIGHTS & PERMISSIONS

2022 Higher Education Press