Dataset Groups Activity Stream State-wise Constrained Policy Optimization State-wise Constrained Policy Optimization (SCPO) is a general-purpose policy search algorithm for state-wise constrained reinforcement learning. BibTex: @dataset{Weiye_Zhao_and_Rui_Chen_and_Yifan_Sun_and_Tianhao_Wei_and_Changliu_Liu_2024, abstract = {State-wise Constrained Policy Optimization (SCPO) is a general-purpose policy search algorithm for state-wise constrained reinforcement learning.}, author = {Weiye Zhao and Rui Chen and Yifan Sun and Tianhao Wei and Changliu Liu}, doi = {10.57702/rxmmrb1p}, institution = {No Organization}, keyword = {'policy optimization', 'reinforcement learning', 'state-wise constraints'}, month = {dec}, publisher = {TIB}, title = {State-wise Constrained Policy Optimization}, url = {https://service.tib.eu/ldmservice/dataset/state-wise-constrained-policy-optimization}, year = {2024} }
