
Safe Policy Optimization with Local Generalized Linear Function Approximations
- Akifumi Wachi, Yunyue Wei, Yanan Sui
- NeurIPS, 2021
I am a Senior Research Scientist at LINE Corporation. My research interests lie primarily in reinforcement learning, and span the entire theory-to-application spectrum from fundamental advances to deployment in real-world systems. Especially, I am interested in how a policy should (and can) be trained and deployed in safety-critiacal problems.
I am from Japan. My Japanese name is 和地 瞭良.
My core research interest is in reinforcement learning for reliable sequential decision making for safety-critical systems. My current research interests can be broadly organized into three overlapping groups:
Safe Reinforcement Learning: study how to develop reinforcement learning approaches with certifiable safety guarantees.
Adversarial Testing via Reinforcement Learning: study how to utlize reinforcement learning approaches for testing safety critical systems and finding failure cases.
Reinforcement Learning × Natural Language Processing: study how to apply reinforcement learning approaches in natural language processing tasks.