4 papers
ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning
Daiki E. Matsunaga, Junho Na, Tri Wahyu Guntara +4
Cooperative tasks in Multi-Agent Reinforcement Learning (MARL) require agents to collectively maximize a shared return. Under the Centralized Training with Decentralized Execution…
GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets
Oh Joon Kwon, Daiki E. Matsunaga, Kee-Eung Kim
A critical component of the current generation of language models is preference alignment, which aims to precisely control the model's behavior to meet human needs and values. The…
Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL
Sungyoon Kim, Yunseon Choi, Daiki E. Matsunaga +1
Offline Goal-Conditioned Reinforcement Learning (Offline GCRL) is an important problem in RL that focuses on acquiring diverse goal-oriented skills solely from pre-collected behavi…
AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation
Daiki E. Matsunaga, Jongmin Lee, Jaeseok Yoon +3
One of the main challenges in offline Reinforcement Learning (RL) is the distribution shift that arises from the learned policy deviating from the data collection policy. This is o…