Learning in two-player zero-sum partially observable Markov games with perfect recall

von Kozuno, Tadashi
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 15 of 36 (2022)

Confident Approximate Policy Iteration for Efficient Local Planning in qπ-realizable MDPs

von Weisz, Gellért
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 33 of 50 (2023)

Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation

von Tang, Yunhao
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 7 of 36 (2022)

Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning

von Furuta, Hiroki
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 12 of 36 (2022)

LEVERAGE THE AVERAGE: AN ANALYSIS OF KL REGULARIZATION IN REINFORCEMENT LEARNING

von Vieillard, Nino
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 15 of 27 (2021)

POLICY INFORMATION CAPACITY: INFORMATION-THEORETIC MEASURE FOR TASK COMPLEXITY IN DEEP REINFORCEMENT LEARNING

von FURUTA, HIROKI
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 5 of 16 (2022)

REVISITING PENG'S Q() FOR MODERN REINFORCEMENT LEARNING

von KOZUNO, TADASHI
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 8 of 16 (2022)