5 citations · 18 across the 33 of their papers we have counts for
36 papers
Thompson Sampling for Learning in Zero-Sum Games
Kenshi Abe, Kaito Ariu, Po-An Wang
Thompson sampling (TS) achieves logarithmic and asymptotically optimal regret in classical stochastic bandits, but its behavior in multi-agent learning remains less understood. We…
Linear Convergence in Games with Delayed Feedback via Extra Prediction
Yuma Fujimoto, Kenshi Abe, Kaito Ariu
Feedback delays are inevitable in real-world multi-agent learning. They are known to severely degrade performance, and the convergence rate under delayed feedback is still unclear,…
Consensus Group Relative Policy Optimization for Text Generation
Yuki Ichihara, Yuu Jinnai, Kaito Ariu +1
Many strong decoding methods for text generation follow a sample-and-rerank paradigm: they draw multiple candidates, score each under a utility (reward) function using consensus ac…
What you reward is what you learn: Comparing rewards for online speech policy optimization in public HRI
Sichao Song, Yuki Okafuji, Kaito Ariu +1
Designing policies that are both efficient and acceptable for conversational service robots in open and diverse environments is non-trivial. Unlike fixed, hand-tuned parameters, on…
Learning from Delayed Feedback in Games via Extra Prediction
Yuma Fujimoto, Kenshi Abe, Kaito Ariu
This study raises and addresses the problem of time-delayed feedback in learning in games. Because learning in games assumes that multiple agents independently learn their strategi…
Asymmetric Perturbation in Solving Bilinear Saddle-Point Optimization
Kenshi Abe, Mitsuki Sakamoto, Kaito Ariu +1
This paper proposes asymmetric perturbation, where only one player's payoff function is perturbed, for solving bilinear saddle-point optimization problems, commonly arising in mini…
Policy Testing in Markov Decision Processes
Kaito Ariu, Po-An Wang, Alexandre Proutiere +1
We study the policy testing problem in discounted Markov decision processes (MDPs) in the fixed-confidence setting under a generative model with static sampling. The goal is to dec…
Evaluation of Best-of-N Sampling Strategies for Language Model Alignment
Yuki Ichihara, Yuu Jinnai, Tetsuro Morimura +4
Best-of-N (BoN) sampling with a reward model has been shown to be an effective strategy for aligning Large Language Models (LLMs) with human preferences at the time of decoding. Bo…
Theoretical Guarantees for Minimum Bayes Risk Decoding
Yuki Ichihara, Yuu Jinnai, Kaito Ariu +2
Minimum Bayes Risk (MBR) decoding optimizes output selection by maximizing the expected utility value of an underlying human distribution. While prior work has shown the effectiven…
On the Power of Perturbation under Sampling in Solving Extensive-Form Games
Wataru Masaka, Mitsuki Sakamoto, Kenshi Abe +3
We investigate how perturbation does and does not improve the Follow-the-Regularized-Leader (FTRL) algorithm in solving imperfect-information extensive-form games under sampling, w…
Time-Varyingness in Auction Breaks Revenue Equivalence
Yuma Fujimoto, Kaito Ariu, Kenshi Abe
Auction is applied for trade with various mechanisms. A simple but practical question is which mechanism, typically first-price or second-price auctions, is preferred from the pers…
Last Iterate Convergence in Monotone Mean Field Games
Noboru Isobe, Kenshi Abe, Kaito Ariu
In the Lasry--Lions framework, Mean-Field Games (MFGs) model interactions among an infinite number of agents. However, existing algorithms either require strict monotonicity or onl…
Boosting Perturbed Gradient Ascent for Last-Iterate Convergence in Games
Kenshi Abe, Mitsuki Sakamoto, Kaito Ariu +1
This paper presents a payoff perturbation technique, introducing a strong convexity to players' payoff functions in games. This technique is specifically designed for first-order m…
Synchronization in Learning in Periodic Zero-Sum Games Triggers Divergence from Nash Equilibrium
Yuma Fujimoto, Kaito Ariu, Kenshi Abe
Learning in zero-sum games studies a situation where multiple agents competitively learn their strategy. In such multi-agent learning, we often see that the strategies cycle around…
Matroid Semi-Bandits in Sublinear Time
Ruo-Chun Tzeng, Naoto Ohsaka, Kaito Ariu
We study the matroid semi-bandits problem, where at each round the learner plays a subset of arms from a feasible set, and the goal is to maximize the expected cumulative linea…
Global Behavior of Learning Dynamics in Zero-Sum Games with Memory Asymmetry
Yuma Fujimoto, Kaito Ariu, Kenshi Abe
This study examines the global behavior of dynamics in learning in games between two players, X and Y. We consider the simplest situation for memory asymmetry between two players:…
Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment
Yuu Jinnai, Tetsuro Morimura, Kaito Ariu +1
Best-of-N (BoN) sampling with a reward model has been shown to be an effective strategy for aligning Large Language Models (LLMs) to human preferences at the time of decoding. BoN…
Nash Equilibrium and Learning Dynamics in Three-Player Matching -Action Games
Yuma Fujimoto, Kaito Ariu, Kenshi Abe
Learning in games discusses the processes where multiple players learn their optimal strategies through the repetition of game plays. The dynamics of learning between two players i…
Return-Aligned Decision Transformer
Tsunehiko Tanaka, Kenshi Abe, Kaito Ariu +2
Traditional approaches in offline reinforcement learning aim to learn the optimal policy that maximizes the cumulative reward, also known as return. It is increasingly important to…
Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding
Yuu Jinnai, Kaito Ariu
Minimum Bayes-Risk (MBR) decoding is shown to be a powerful alternative to beam search decoding for a wide range of text generation tasks. However, MBR requires a huge amount of ti…
Model-Based Minimum Bayes Risk Decoding for Text Generation
Yuu Jinnai, Tetsuro Morimura, Ukyo Honda +2
Minimum Bayes Risk (MBR) decoding has been shown to be a powerful alternative to beam search decoding in a variety of text generation tasks. MBR decoding selects a hypothesis from…
On Universally Optimal Algorithms for A/B Testing
Po-An Wang, Kaito Ariu, Alexandre Proutiere
We study the problem of best-arm identification with fixed budget in stochastic multi-armed bandits with Bernoulli rewards. For the problem with two arms, also known as the A/B tes…
Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model
Kaito Ariu, Alexandre Proutiere, Se-Young Yun
In this paper, we investigate the problem of recovering hidden communities in the Labeled Stochastic Block Model (LSBM) with a finite number of clusters whose sizes grow linearly w…
Exploration of Unranked Items in Safe Online Learning to Re-Rank
Hiroaki Shiino, Kaito Ariu, Kenshi Abe +1
Bandit algorithms for online learning to rank (OLTR) problems often aim to maximize long-term revenue by utilizing user feedback. From a practical point of view, however, such algo…