4 papers
Redesigning Regularization for Effective Policy Smoothing
Taisuke Kobayashi, Naoto Yamanaka
This paper proposes a novel regularization design to effectively smooth policy functions in reinforcement learning. While regularization that enhances ``global'' Lipschitz continui…
CubeDAgger: Interactive Imitation Learning for Dynamic Systems with Efficient yet Low-risk Interaction
Taisuke Kobayashi
Interactive imitation learning makes an agent's control policy robust by stepwise supervisions from an expert. The recent algorithms mostly employ expert-agent switching systems to…
Flexible Empowerment at Reasoning with Extended Best-of-N Sampling
Taisuke Kobayashi
This paper proposes a novel method that incorporates empowerment when reasoning actions in reinforcement learning (RL), thereby achieving the flexibility of exploration-exploitatio…
Skin-Machine Interface with Multimodal Contact Motion Classifier
Alberto Confente, Takanori Jin, Taisuke Kobayashi +2
This paper proposes a novel framework for utilizing skin sensors as a new operation interface of complex robots. The skin sensors employed in this study possess the capability to q…