My research attempts to address on-line action selection in reinforcement learning from a Bayesian perspective. The idea is to develop more effective action selection techniques b...
To effectively generate a fast and consistent apartment construction project network, Hyundai and KAIST have developed a case and constraint based project planning expert system f...
Kyoung Jun Lee, Hyun Woo Kim, Jae Kyu Lee, Tae Hwa...
Table lookup with interpolation is used for many learning and adaptation tasks. Redundant mappings capture the important concept of \motor skill," which is important in real,...
d Abstract) Piyoosh Mukhija IIIT Hyderabad Rahul Sawhney IIIT Hyderabad K Madhava Krishna IIIT Hyderabad We present an algorithm for multi robotic exploration of an unknown terrai...
Piyoosh Mukhija, Rahul Sawhney, K. Madhava Krishna
This paper analyzes the worst-case efficiency ratio of falsename-proof combinatorial auction mechanisms. False-nameproofness generalizes strategy-proofness by assuming that a bidd...
Atsushi Iwasaki, Vincent Conitzer, Yoshifusa Omori...