Tatsuya Harada

Rethinking Policy Diversity in Ensemble Policy Gradient in Large-Scale Reinforcement Learning

R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation

Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets

Resource-Efficient Model-Free Reinforcement Learning for Board Games

Aligning Large Language Model Behavior with Human Citation Preferences

CapTalk: Text-Guided Stylization and Speech-Driven 3D Head Animation

Harnessing Bayesian Optimism with Dual Policies in Reinforcement Learning

Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning

I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions

Dr. RAW: Towards General High-Level Vision from RAW with Efficient Task Conditioning

T2V2: A Unified Non-Autoregressive Model for Speech Recognition and Synthesis via Multitask Learning

Annealed Implicit Q-learning in Online Reinforcement Learning