%0 Journal Article %1 journals/tsp/TianLHL22 %A Tian, Chang %A Liu, An %A Huang, Guan %A Luo, Wu %D 2022 %J IEEE Trans. Signal Process. %K dblp %P 1609-1624 %T Successive Convex Approximation Based Off-Policy Optimization for Constrained Reinforcement Learning. %U http://dblp.uni-trier.de/db/journals/tsp/tsp70.html#TianLHL22 %V 70

@article{journals/tsp/TianLHL22, added-at = {2022-05-18T00:00:00.000+0200}, author = {Tian, Chang and Liu, An and Huang, Guan and Luo, Wu}, biburl = {https://www.bibsonomy.org/bibtex/2d28e35f6be8cd9285d9010f767c46fdb/dblp}, ee = {https://doi.org/10.1109/TSP.2022.3158737}, interhash = {70f5ee0f3787916fae7be7a1d33bae2e}, intrahash = {d28e35f6be8cd9285d9010f767c46fdb}, journal = {IEEE Trans. Signal Process.}, keywords = {dblp}, pages = {1609-1624}, timestamp = {2024-04-09T01:59:27.000+0200}, title = {Successive Convex Approximation Based Off-Policy Optimization for Constrained Reinforcement Learning.}, url = {http://dblp.uni-trier.de/db/journals/tsp/tsp70.html#TianLHL22}, volume = 70, year = 2022 }