Alekh Agarwal, Mikael Henaff, Sham M. Kakade, Wen Sun. PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning. In Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, Hsuan-Tien Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. 2020. [doi]
@inproceedings{AgarwalHKS20, title = {PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning}, author = {Alekh Agarwal and Mikael Henaff and Sham M. Kakade and Wen Sun}, year = {2020}, url = {https://proceedings.neurips.cc/paper/2020/hash/9b3a9fb4db30fc6594ec3990cbc09932-Abstract.html}, researchr = {https://researchr.org/publication/AgarwalHKS20}, cites = {0}, citedby = {0}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria-Florina Balcan and Hsuan-Tien Lin}, }