PP-PG: Combining Parameter Perturbation with Policy Gradient Methods for Effective and Efficient Explorations in Deep Reinforcement Learning.

@article{li-2021-pppg, author = {Shilei Li and Meng Li and Jiongming Su and Shaofei Chen and Zhimin Yuan and Qing Ye}, title = {{PP-PG: Combining Parameter Perturbation with Policy Gradient Methods for Effective and Efficient Explorations in Deep Reinforcement Learning}}, journal = {ACM Transactions on Intelligent Systems and Technology (TIST)}, volume = {12}, number = {3}, pages = {35:1--35:21}, year = {2021}, url = {https://doi.org/10.1145/3452008}, doi = {https://doi.org/10.1145/3452008} }