The Sufficiency of Off-Policyness and Soft Clipping: PPO Is Still Insufficient according to an Off-Policy Measure

Xing Chen, Dongcui Diao, Hechang Chen, Hengshuai Yao, Haiyin Piao, Zhixiao Sun, Zhiwei Yang 0005, Randy Goebel, Bei Jiang, Yi Chang. The Sufficiency of Off-Policyness and Soft Clipping: PPO Is Still Insufficient according to an Off-Policy Measure. In Brian Williams 0001, Yiling Chen 0001, Jennifer Neville, editors, Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2023, Washington, DC, USA, February 7-14, 2023. pages 7078-7086, AAAI Press, 2023. [doi]

Authors

Xing Chen

This author has not been identified. Look up 'Xing Chen' in Google

Dongcui Diao

This author has not been identified. Look up 'Dongcui Diao' in Google

Hechang Chen

This author has not been identified. Look up 'Hechang Chen' in Google

Hengshuai Yao

This author has not been identified. Look up 'Hengshuai Yao' in Google

Haiyin Piao

This author has not been identified. Look up 'Haiyin Piao' in Google

Zhixiao Sun

This author has not been identified. Look up 'Zhixiao Sun' in Google

Zhiwei Yang 0005

This author has not been identified. Look up 'Zhiwei Yang 0005' in Google

Randy Goebel

This author has not been identified. Look up 'Randy Goebel' in Google

Bei Jiang

This author has not been identified. Look up 'Bei Jiang' in Google

Yi Chang

This author has not been identified. Look up 'Yi Chang' in Google