Daiki E. Matsunaga

3 papers · 2023–2024 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

AAAI (1) EMNLP (1) NeurIPS (1)

Top co-authors

Kee-eung Kim (3) Jongmin Lee (1) Oh Joon Kwon (1) Sungyoon Kim (1) Stefanos Leonardos (1) Jaeseok Yoon (1) Pieter Abbeel (1) Yunseon Choi (1)

Research topics

Reinforcement Learning (3) Methods (3) Artificial Intelligence (2) Deep Learning (2) Core AI (2) Models (2) Machine Learning (1) Applications (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1)

Keywords

offline reinforcement learning (3) direct preference optimization (1) preference alignment (1) conditional generation (1) stationary distribution (1) diffusion model (1) language model (1) reward model (1) out-of-distribution action (1) generative flow network (1) value decomposition (1) goal-conditioned planning (1) large language model (1) multi-agent system (1) trajectory stitching (1) diversity seeking (1) reinforcement learning (1) nash policy (1)

Papers

GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets EMNLP 2024 Stitching Sub-trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL AAAI 2024 AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation NeurIPS 2023