1 citations · 1 across the 14 of their papers we have counts for
12 papers · 1 filter
Randomized Exploration for Linear Bandits via Absolute Perturbations
Toshinori Kitamura, Shuai Liu, Csaba Szepesvári
In stochastic linear bandits, the canonical Upper Confidence Bound (UCB) algorithm admits a simple frequentist regret analysis but can be computationally demanding, while Thompson…
Offline-to-Online Learning in Linear Bandits
Kushagra Chandak, Toshinori Kitamura, Xiaoqi Tan
We study online learning with an additional offline dataset in the stochastic linear bandit setting. Although this problem arises frequently in practice, the offline-to-online trad…
Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
Soichiro Nishimori, Paavo Parmas, Sotetsu Koyamada +4
In reinforcement learning (RL), agents benefit from exploration only because they repeatedly encounter similar states: trying different actions can improve performance or reduce un…
Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
Toshinori Kitamura, Arnob Ghosh, Tadashi Kozuno +5
We study the reinforcement learning (RL) problem in a constrained Markov decision process (CMDP), where an agent explores the environment to maximize the expected cumulative reward…
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form
Toshinori Kitamura, Tadashi Kozuno, Wataru Kumagai +6
Designing a safe policy for uncertain environments is crucial in real-world control systems. However, this challenge remains inadequately addressed within the Markov decision proce…
A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
Toshinori Kitamura, Tadashi Kozuno, Masahiro Kato +6
We study a primal-dual (PD) reinforcement learning (RL) algorithm for online constrained Markov decision processes (CMDPs). Despite its widespread practical use, the existing theor…
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang +12
Mirror descent value iteration (MDVI), an abstraction of Kullback-Leibler (KL) and entropy-regularized reinforcement learning (RL), has served as the basis for recent high-performi…
KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal
Tadashi Kozuno, Wenhao Yang, Nino Vieillard +10
In this work, we consider and analyze the sample complexity of model-free reinforcement learning with a generative model. Particularly, we analyze mirror descent value iteration (M…
ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives
Toshinori Kitamura, Ryo Yonetani
We present ShinRL, an open-source library specialized for the evaluation of reinforcement learning (RL) algorithms from both theoretical and practical perspectives. Existing RL lib…
Geometric Value Iteration: Dynamic Error-Aware KL Regularization for Reinforcement Learning
Toshinori Kitamura, Lingwei Zhu, Takamitsu Matsubara
The recent boom in the literature on entropy-regularized reinforcement learning (RL) approaches reveals that Kullback-Leibler (KL) regularization brings advantages to RL algorithms…
Cautious Policy Programming: Exploiting KL Regularization in Monotonic Policy Improvement for Reinforcement Learning
Lingwei Zhu, Toshinori Kitamura, Takamitsu Matsubara
In this paper, we propose cautious policy programming (CPP), a novel value-based reinforcement learning (RL) algorithm that can ensure monotonic policy improvement during learning.…
Cautious Actor-Critic
Lingwei Zhu, Toshinori Kitamura, Takamitsu Matsubara
The oscillating performance of off-policy learning and persisting errors in the actor-critic (AC) setting call for algorithms that can conservatively learn to suit the stability-cr…