Kuspriyanto Kuspriyanto

About

Kuspriyanto Kuspriyanto is a researcher in artificial intelligence, with a primary focus on reinforcement learning and multi-agent systems. His work addresses the critical challenge of accelerating reinforcement learning in environments where internal knowledge or human intervention is unavailable. In his notable 2014 paper, "Online State Elimination in Accelerated Reinforcement Learning," he proposed a novel approach that eliminates unnecessary states during the learning process, offering a solution to RL acceleration when traditional methods like reward shaping or transfer learning cannot be applied. This contribution has been cited 2 times, reflecting its niche but important impact on the field. His 2013 paper, "Multi Agent Reinforcement Learning for Gridworld Soccer Leadingpass," explores cooperative strategies in multi-agent settings, specifically in gridworld soccer simulations, and has also garnered 2 citations. Kuspriyanto’s research is particularly valuable for advancing autonomous learning systems that must operate without external guidance, making his work relevant for students and researchers interested in efficient, self-contained reinforcement learning algorithms.

Research Focus

Key Achievements

Top Papers

1. 1
   Multi Agent Reinforcement Learning for Gridworld Soccer Leadingpass

   2 citations · 2013
2. 2
   Online State Elimination in Accelerated reinforcement Learning

   2 citations · 2014

Key Collaborators

Contact & Links