@inproceedings{onpolicytrustregionpolicyoptimisation, title = {On-Policy Trust Region Policy Optimisation with Replay Buffers}, author = {Dmitry Kangin and Nicolas Pugeault}, year = {2019}, booktitle = {ICLR 2019 5}, eprint = {1901.06212}, archivePrefix = {arXiv}, url = {http://arxiv.org/abs/1901.06212v1}, }