MSVPO

Author's implementation of "Mean-Semivariance Policy Optimization via Risk-Averse".

Installation

This code is based my forked version of rlpyt. To reproduce the results in paper, please run python run_exp.py. Note that this python file contains all the hyperparameters I have tried on 8 GPUs. Please set your hyperparameters manually before your experiments.

Bibtex

@article{ma2022mean-semivariance,
    title={Mean-Semivariance Policy Optimization via Risk-Averse},
    author={Ma, Xiaoteng and Ma, Shuai and Xia, Li and Zhao, Qianchuan},
    journal={Jounal of Artificial Intelligence Research},
    volume={75},
    pages={569-595},
    year={2022}
}