Policy gradient approaches for multi-objective sequential decision making: A comparison. Parisi, S., Pirotta, M., Smacchia, N., Bascetta, L., & Restelli, M. In Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), 2014 IEEE Symposium on, pages 1--8, 2014.
doi  bibtex   
@inproceedings{parisi_policy_2014,
	title = {Policy gradient approaches for multi-objective sequential decision making: {A} comparison},
	doi = {10.1109/ADPRL.2014.7010618},
	booktitle = {Adaptive {Dynamic} {Programming} and {Reinforcement} {Learning} ({ADPRL}), 2014 {IEEE} {Symposium} on},
	author = {Parisi, Simone and Pirotta, Matteo and Smacchia, Nicola and Bascetta, Luca and Restelli, Marcello},
	year = {2014},
	keywords = {Multiobjective optimization, Reinforcement learning},
	pages = {1--8}
}

Downloads: 0