Center for Advanced Intelligence Project

Three papers from the RIKEN Center for Advanced Intelligence Project (AIP) have been accepted at The Second Reinforcement Learning Conference (RLC) 2025, an international conference newly established in 2024 focusing on reinforcement learning.

[Website] https://rl-conference.cc/

[Acceptance rate]
Out of 295 submissions, 115 papers were accepted, resulting in an acceptance rate of 39.0%.

• Offline Reinforcement Learning with Domain-Unlabeled Data
  Soichiro Nishimori (The University of Tokyo / RIKEN AIP)
  Xin-Qiang Cai (RIKEN AIP)
  Johannes Ackermann (The University of Tokyo / RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
• Offline Reinforcement Learning with Wasserstein Regularization via Optimal Transport Maps
  Motoki Omura (The University of Tokyo)
  Yusuke Mukuta (The University of Tokyo / RIKEN AIP)
  Kazuki Ota (The University of Tokyo)
  Takayuki Osa (RIKEN AIP)
  Tatsuya Harada (The University of Tokyo/ RIKEN AIP)
• Recursive Reward Aggregation
  Yuting Tang (The University of Toky)
  Yivan Zhang (The University of Tokyo / RIKEN AIP)
  Johannes Ackermann (The University of Tokyo / RIKEN AIP)
  Yu-Jie Zhang (RIKEN AIP)
  Soichiro Nishimori (The University of Tokyo / RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)

Related Laboratories