Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning

Shuang Qiu, Lingxiao Wang, Chenjia Bai, Zhuoran Yang, Zhaoran Wang. Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning. In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu 0001, Sivan Sabato, editors, International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA. Volume 162 of Proceedings of Machine Learning Research, pages 18168-18210, PMLR, 2022. [doi]

Authors

Shuang Qiu

This author has not been identified. Look up 'Shuang Qiu' in Google

Lingxiao Wang

This author has not been identified. Look up 'Lingxiao Wang' in Google

Chenjia Bai

This author has not been identified. Look up 'Chenjia Bai' in Google

Zhuoran Yang

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

Zhaoran Wang

This author has not been identified. Look up 'Zhaoran Wang' in Google