activity
20202026
most citedModel-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall

2 citations · 5 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback

Côme Fiegel, Pierre Ménard, Tadashi Kozuno +2

We study the problem of learning in zero-sum matrix games with repeated play and bandit feedback. Specifically, we focus on developing uncoupled algorithms that guarantee, without…

cs.LG2026

Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier

Come Fiegel, Pierre Menard, Tadashi Kozuno +2

We study the problem of learning minimax policies in zero-sum matrix games. Fiegel et al. (2025) recently showed that achieving last-iterate convergence in this setting is harder w…

cs.LG2023

DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm

Yunhao Tang, Tadashi Kozuno, Mark Rowland +4

Multi-step learning applies lookahead over multiple time steps and has proved valuable in policy evaluation settings. However, in the optimal control case, the impact of multi-step…

cs.LG2023

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…

cs.LG2022

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…

cs.LG2021★ 1 cited

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

Yunhao Tang, Tadashi Kozuno, Mark Rowland +2

Model-agnostic meta-reinforcement learning requires estimating the Hessian matrix of value functions. This is challenging from an implementation perspective, as repeatedly differen…