4 citations · 7 across the 5 of their papers we have counts for
5 papers
e-person Architecture and Framework for Human-AI Co-adventure Relationship
Kanako Esaki, Tadayuki Matsumura, Yang Shao +1
This paper proposes the e-person architecture for constructing a unified and incremental development of AI ethics. The e-person architecture takes the reduction of uncertainty thro…
Environment-Centric Active Inference
Kanako Esaki, Tadayuki Matsumura, Takeshi Kato +3
To handle unintended changes in the environment by agents, we propose an environment-centric active inference EC-AIF in which the Markov Blanket of active inference is defined star…
Response Style Characterization for Repeated Measures Using the Visual Analogue Scale
Shunsuke Minusa, Tadayuki Matsumura, Kanako Esaki +3
Self-report measures (e.g., Likert scales) are widely used to evaluate subjective health perceptions. Recently, the visual analog scale (VAS), a slider-based scale, has become popu…
The impact of individual information exchange strategies on the distribution of social wealth
Yang Shao, Hirokazu Atsumori, Tadayuki Matsumura +3
Wealth distribution is a complex and critical aspect of any society. Information exchange is considered to have played a role in shaping wealth distribution patterns, but the speci…
Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks
Yang Shao, Quan Kong, Tadayuki Matsumura +3
We present Mask Atari, a new benchmark to help solve partially observable Markov decision process (POMDP) problems with Deep Reinforcement Learning (DRL)-based approaches. To achie…