@inproceedings{ijcai2019p475, title = {Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning}, author = {Shi, Wenjie and Song, Shiji and Wu, Cheng}, booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI-19}}, publisher = {International Joint Conferences on Artificial Intelligence Organization}, pages = {3425--3431}, year = {2019}, month = {7}, doi = {10.24963/ijcai.2019/475}, url = {https://doi.org/10.24963/ijcai.2019/475}, }