ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Ted Moskovitz, Brendan O'Donoghue, Vivek Veeriah, Sebastian Flennerhag, Satinder Singh 0001, Tom Zahavy. ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs. In Andreas Krause 0001, Emma Brunskill, KyungHyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett, editors, International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA. Volume 202 of Proceedings of Machine Learning Research, pages 25303-25336, PMLR, 2023. [doi]

This author has not been identified. Look up 'Ted Moskovitz' in GoogleThis author has not been identified. Look up 'Brendan O'Donoghue' in GoogleThis author has not been identified. Look up 'Vivek Veeriah' in GoogleThis author has not been identified. Look up 'Sebastian Flennerhag' in GoogleThis author has not been identified. Look up 'Satinder Singh 0001' in GoogleThis author has not been identified. Look up 'Tom Zahavy' in Google

runs on WebDSL