Hisashi Handa

About

Hisashi Handa is a leading researcher in the intersection of reinforcement learning, evolutionary computation, and robotics. His most influential work focuses on adaptive state-space construction for reinforcement learning, particularly in robot navigation. In his highly cited 2002 paper (17 citations), Handa introduced a novel method using Adaptive Resonance Theory (ART) neural networks combined with a contradiction resolution mechanism to enable agents to dynamically build appropriate state representations from sensory inputs. This approach, inspired by Piaget's theory of cognitive development, allows robots to incrementally construct state spaces that improve learning efficiency and adaptability in complex environments. Handa has also explored dimensionality reduction through manifold learning for evolutionary systems, addressing the critical challenge of redundant sensory inputs in robotics. His work on coevolutionary fuzzy classifier systems further extends perception-action rule acquisition for mobile robots. With over 38 citations across his key publications, Handa's contributions have significantly advanced the development of intelligent, adaptive robotic systems capable of learning from their environment without pre-defined state spaces.

Research Focus

Key Achievements

Top Papers

1. 1
   Adaptive state construction for reinforcement learning and its application to robot navigation problems

   17 citations · 2002
2. 2
   An Incremental State-Space Construction Based on the Notion of Contradiction for Reinforcement Learning

   10 citations · 2002
3. 3
   On the effect of dimensionality reduction by Manifold Learning for Evolutionary Learning

   5 citations · 2011
4. 4
   Dimension reduction by Manifold Learning for Evolutionary Learning with redundant sensory inputs

   3 citations · 2010
5. 5
   Perception-action rule acquisition by coevolutionary fuzzy classifier system

   3 citations · 2002

Key Collaborators

Contact & Links