KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal T Kozuno, W Yang, N Vieillard, T Kitamura, Y Tang, J Mei, P Ménard, ... arXiv preprint arXiv:2205.14211, 2022 | 7 | 2022 |
ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives T Kitamura, R Yonetani arXiv preprint arXiv:2112.04123, 2021 | 3 | 2021 |
A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees T Kitamura, T Kozuno, M Kato, Y Ichihara, S Nishimori, A Sannai, ... arXiv preprint arXiv:2401.17780, 2024 | 2 | 2024 |
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice T Kitamura, T Kozuno, Y Tang, N Vieillard, M Valko, W Yang, J Mei, ... International Conference on Machine Learning, 17135-17175, 2023 | 2 | 2023 |
Geometric Value Iteration: Dynamic Error-Aware KL Regularization for Reinforcement Learning T Kitamura, L Zhu, T Matsubara Asian Conference on Machine Learning, 918-931, 2021 | 2 | 2021 |
Cautious policy programming: exploiting KL regularization for monotonic policy improvement in reinforcement learning L Zhu, T Matsubara Machine Learning 112 (11), 4527-4562, 2023 | 1 | 2023 |
Cautious Actor-Critic L Zhu, T Kitamura, M Takamitsu Asian Conference on Machine Learning, 220-235, 2021 | 1 | 2021 |
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form T Kitamura, T Kozuno, W Kumagai, K Hoshino, Y Hosoe, K Kasaura, ... arXiv preprint arXiv:2408.16286, 2024 | | 2024 |
Dynamic KL Regularization in Reinforcement Learning: Theoretical Error Propagation Analysis and an Algorithm T Kitamura Nara Institute of Science and Technology, 2022 | | 2022 |