https://bakanaouji.github.io/ja/publications/asymmetric-perturbation-bilinear-icml-2026/2026-07-07T00:00:00+00:000https://bakanaouji.github.io/ja/publications/2026-07-07T00:00:00+00:00daily0.5https://bakanaouji.github.io/ja/2026-07-07T00:00:00+00:00daily0.5https://bakanaouji.github.io/ja/publications/time-varyingness-auction-aamas-2026/2026-05-27T00:00:00+00:000https://bakanaouji.github.io/ja/publications/policy-testing-mdp-aistats-2026/2026-05-02T00:00:00+00:000https://bakanaouji.github.io/ja/publications/policy-testing-mdp-neurips-2025/2025-12-06T00:00:00+00:000https://bakanaouji.github.io/ja/publications/monotone-mean-field-games-neurips-2025/2025-12-03T00:00:00+00:000https://bakanaouji.github.io/ja/publications/learning-from-delayed-feedback-neurips-2025/2025-12-03T00:00:00+00:000https://bakanaouji.github.io/ja/publications/asymmetric-perturbation-bilinear-ibis-2025/2025-11-12T00:00:00+00:000https://bakanaouji.github.io/ja/publications/policy-testing-mdp-ibis-2025/2025-11-12T00:00:00+00:000https://bakanaouji.github.io/ja/publications/unified-convergence-guarantees-efg-ibis-2025/2025-11-12T00:00:00+00:000https://bakanaouji.github.io/ja/publications/time-varyingness-auction-ibis-2025/2025-11-12T00:00:00+00:000https://bakanaouji.github.io/ja/publications/learning-from-delayed-feedback-ibis-2025/2025-11-12T00:00:00+00:000https://bakanaouji.github.io/ja/publications/additive-reward-non-stationary-bandit-ibis-2025/2025-11-12T00:00:00+00:000https://bakanaouji.github.io/ja/publications/perturbation-under-sampling-efg-fit-2025/2025-09-03T00:00:00+00:000https://bakanaouji.github.io/ja/publications/return-aligned-decision-transformer-tmlr-2025/2025-06-08T00:00:00+00:000https://bakanaouji.github.io/ja/publications/perturbation-under-sampling-efg-jsai-2025/2025-05-27T00:00:00+00:000https://bakanaouji.github.io/ja/publications/synchronization-periodic-zero-sum-jsai-2025/2025-05-27T00:00:00+00:000https://bakanaouji.github.io/ja/publications/alignment-evaluation-llm-jsai-2025/2025-05-27T00:00:00+00:000https://bakanaouji.github.io/ja/publications/global-behavior-zero-sum-games-aamas-2025/2025-05-21T00:00:00+00:000https://bakanaouji.github.io/ja/publications/three-player-matching-games-aamas-2025/2025-05-21T00:00:00+00:000https://bakanaouji.github.io/ja/publications/regularized-best-of-n-naacl-2025/2025-04-30T00:00:00+00:000https://bakanaouji.github.io/ja/publications/boosting-perturbed-gradient-ascent-iclr-2025/2025-04-24T00:00:00+00:000https://bakanaouji.github.io/ja/publications/perturbation-under-sampling-efg-ipsj-2025/2025-03-13T00:00:00+00:000https://bakanaouji.github.io/ja/publications/creative-selection-online-advertising-wsdm-2025/2025-03-11T00:00:00+00:000https://bakanaouji.github.io/ja/publications/alignment-evaluation-llm-nlp-2025/2025-03-10T00:00:00+00:000https://bakanaouji.github.io/ja/publications/state-abstraction-markov-games-aaai-2025/2025-02-27T00:00:00+00:000https://bakanaouji.github.io/ja/publications/synchronization-periodic-zero-sum-aaai-2025/2025-02-27T00:00:00+00:000https://bakanaouji.github.io/ja/publications/evaluation-best-of-n-tmlr-2025/2025-02-15T00:00:00+00:000https://bakanaouji.github.io/ja/publications/perturbation-under-sampling-efg-arxiv-2025/2025-01-28T00:00:00+00:000https://bakanaouji.github.io/ja/publications/filtered-dpo-emnlp-2024/2024-11-12T00:00:00+00:000https://bakanaouji.github.io/ja/publications/perturbation-under-sampling-efg-ibis-2024/2024-11-04T00:00:00+00:000https://bakanaouji.github.io/ja/publications/evaluation-best-of-n-ibis-2024/2024-11-04T00:00:00+00:000https://bakanaouji.github.io/ja/publications/filtered-dpo-ibis-2024/2024-11-04T00:00:00+00:000https://bakanaouji.github.io/ja/publications/monotone-mean-field-games-ibis-2024/2024-11-04T00:00:00+00:000https://bakanaouji.github.io/ja/publications/synchronization-periodic-zero-sum-ibis-2024/2024-11-04T00:00:00+00:000https://bakanaouji.github.io/ja/publications/bayes-risk-preference-optimization-ibis-2024/2024-11-04T00:00:00+00:000https://bakanaouji.github.io/ja/publications/policy-testing-mdp-ibis-2024/2024-11-04T00:00:00+00:000https://bakanaouji.github.io/ja/publications/state-abstraction-markov-games-fit-2024/2024-09-04T00:00:00+00:000https://bakanaouji.github.io/ja/publications/policy-gradient-mcts-rlc-2024/2024-08-10T00:00:00+00:000https://bakanaouji.github.io/ja/publications/filtered-dpo-icml-2024/2024-07-26T00:00:00+00:000https://bakanaouji.github.io/ja/publications/regularized-best-of-n-icml-2024/2024-07-26T00:00:00+00:000https://bakanaouji.github.io/ja/publications/adaptively-perturbed-mirror-descent-icml-2024/2024-07-23T00:00:00+00:000https://bakanaouji.github.io/ja/publications/model-based-mbr-icml-2024/2024-07-23T00:00:00+00:000https://bakanaouji.github.io/ja/publications/distribution-shift-evaluation-rlhf-jsai-2024/2024-05-28T00:00:00+00:000https://bakanaouji.github.io/ja/publications/mutation-driven-ftrl-ipsj-j-2024/2024-05-15T00:00:00+00:000https://bakanaouji.github.io/ja/publications/scalable-fair-exposure-control-www-2024/2024-05-14T00:00:00+00:000https://bakanaouji.github.io/ja/publications/learning-fair-division-aistats-2024/2024-05-02T00:00:00+00:000https://bakanaouji.github.io/ja/publications/state-abstraction-markov-games-ipsj-2024/2024-03-15T00:00:00+00:000https://bakanaouji.github.io/ja/publications/medical-residency-match-ipsj-2024/2024-03-15T00:00:00+00:000https://bakanaouji.github.io/ja/publications/memory-asymmetry-heteroclinic-orbits-aaai-2024/2024-02-22T00:00:00+00:000https://bakanaouji.github.io/ja/publications/adaptively-perturbed-mirror-descent-ibis-2023/2023-10-29T00:00:00+00:000https://bakanaouji.github.io/ja/publications/multi-memory-games-ibis-2023/2023-10-29T00:00:00+00:000https://bakanaouji.github.io/ja/publications/perturbation-under-sampling-efg-ibis-2023/2023-10-29T00:00:00+00:000https://bakanaouji.github.io/ja/publications/learning-fair-division-ibis-2023/2023-10-29T00:00:00+00:000https://bakanaouji.github.io/ja/publications/learning-fair-division-fit-2023/2023-09-06T00:00:00+00:000https://bakanaouji.github.io/ja/publications/medical-residency-match-fit-2023/2023-09-06T00:00:00+00:000https://bakanaouji.github.io/ja/publications/multi-memory-games-ijcai-2023/2023-08-22T00:00:00+00:000https://bakanaouji.github.io/ja/publications/safe-online-learning-to-rerank-sigir-2023/2023-07-24T00:00:00+00:000https://bakanaouji.github.io/ja/publications/guided-dialog-adversarial-arxiv-2023/2023-07-13T00:00:00+00:000https://bakanaouji.github.io/ja/publications/learning-fair-division-jsai-2023/2023-06-06T00:00:00+00:000https://bakanaouji.github.io/ja/publications/mutation-mwu-efg-jsai-2023/2023-06-06T00:00:00+00:000https://bakanaouji.github.io/ja/publications/last-iterate-full-noisy-feedback-aistats-2023/2023-04-25T00:00:00+00:000https://bakanaouji.github.io/ja/publications/decision-transformer-dialogue-nlp-2023/2023-03-13T00:00:00+00:000https://bakanaouji.github.io/ja/publications/guided-dialog-adversarial-nlp-2023/2023-03-13T00:00:00+00:000https://bakanaouji.github.io/ja/publications/learning-fair-division-ipsj-2023/2023-03-02T00:00:00+00:000https://bakanaouji.github.io/ja/publications/medical-residency-match-ipsj-2023/2023-03-02T00:00:00+00:000https://bakanaouji.github.io/ja/publications/last-iterate-full-noisy-feedback-ibis-2022/2022-11-20T00:00:00+00:000https://bakanaouji.github.io/ja/publications/thresholded-lasso-bandit-ibis-2022/2022-11-20T00:00:00+00:000https://bakanaouji.github.io/ja/publications/policy-gradient-mcts-ibis-2022/2022-11-20T00:00:00+00:000https://bakanaouji.github.io/ja/publications/scalable-fair-exposure-control-ibis-2022/2022-11-20T00:00:00+00:000https://bakanaouji.github.io/ja/publications/scalable-fair-exposure-control-recsys-2022/2022-09-23T00:00:00+00:000https://bakanaouji.github.io/ja/publications/mutation-driven-ftrl-fit-2022/2022-09-13T00:00:00+00:000https://bakanaouji.github.io/ja/publications/mutation-driven-ftrl-uai-2022/2022-08-02T00:00:00+00:000https://bakanaouji.github.io/ja/publications/medical-residency-match-ijcai-2022/2022-07-26T00:00:00+00:000https://bakanaouji.github.io/ja/publications/thresholded-lasso-bandit-icml-2022/2022-07-19T00:00:00+00:000https://bakanaouji.github.io/ja/publications/mutation-driven-ftrl-jsai-2022/2022-06-14T00:00:00+00:000https://bakanaouji.github.io/ja/publications/multi-agent-rl-cournot-competition-ipsj-2022/2022-03-03T00:00:00+00:000https://bakanaouji.github.io/ja/publications/mutation-driven-ftrl-ipsj-2022/2022-03-03T00:00:00+00:000https://bakanaouji.github.io/ja/publications/american-football-cfr-aaai-2022/2022-02-28T00:00:00+00:000https://bakanaouji.github.io/ja/publications/direct-quadratic-utility-maximization-neurips-2021/2021-12-13T00:00:00+00:000https://bakanaouji.github.io/ja/publications/misperception-repeated-games-ibis-2021/2021-11-10T00:00:00+00:000https://bakanaouji.github.io/ja/publications/misperception-repeated-games-orsj-2021/2021-09-16T00:00:00+00:000https://bakanaouji.github.io/ja/publications/american-football-cfr-fit-2021/2021-08-25T00:00:00+00:000https://bakanaouji.github.io/ja/publications/misperception-repeated-games-fit-2021/2021-08-25T00:00:00+00:000https://bakanaouji.github.io/ja/publications/off-policy-exploitability-evaluation-aamas-2021/2021-05-05T00:00:00+00:000https://bakanaouji.github.io/ja/publications/off-policy-q-learning-markov-games-gpw-2020/2020-11-14T00:00:00+00:000https://bakanaouji.github.io/ja/publications/off-policy-evaluation-bandits-guide-arxiv-2020/2020-10-23T00:00:00+00:000https://bakanaouji.github.io/ja/publications/bidding-agent-first-price-auction-aaai-2020/2020-02-08T00:00:00+00:000https://bakanaouji.github.io/ja/publications/nash-equilibrium-strategy-hanafuda-ibis-2019/2019-11-20T00:00:00+00:000https://bakanaouji.github.io/ja/publications/bayesian-optimization-low-budget-arxiv-2019/2019-11-18T00:00:00+00:000https://bakanaouji.github.io/ja/publications/bayesian-optimization-low-budget-jsai-2019/2019-06-04T00:00:00+00:000https://bakanaouji.github.io/ja/publications/non-stationary-bandit-hpo-ibis-2018/2018-11-04T00:00:00+00:000https://bakanaouji.github.io/ja/publications/exemplar-policy-optimization-ee-jpnsec-2017/2017-03-13T00:00:00+00:000https://bakanaouji.github.io/ja/publications/exemplar-policy-optimization-multimodal-ssi-2016/2016-12-06T00:00:00+00:000https://bakanaouji.github.io/ja/publications/exemplar-policy-optimization-nes-sice-se-2016/2016-03-07T00:00:00+00:000https://bakanaouji.github.io/ja/research/bandits-online-learning/daily0.5https://bakanaouji.github.io/ja/research/fairness-recsys-allocation/daily0.5https://bakanaouji.github.io/ja/research/language-model-alignment/daily0.5https://bakanaouji.github.io/ja/research/learning-dynamics-equilibrium-games/daily0.5https://bakanaouji.github.io/ja/research/reinforcement-learning-sequential-decision/daily0.5https://bakanaouji.github.io/ja/research/daily0.5