Sciweavers

53 search results - page 8 / 11
» Shaping multi-agent systems with gradient reinforcement lear...
Sort
View
RAS
2006
105views more  RAS 2006»
14 years 9 months ago
Reinforcement learning for quasi-passive dynamic walking of an unstable biped robot
A class of biped locomotion called Passive Dynamic Walking (PDW) has been recognized to be efficient in energy consumption and a key to understand human walking. Although PDW is s...
Kentarou Hitomi, Tomohiro Shibata, Yutaka Nakamura...
ICONIP
2007
14 years 11 months ago
Finding Exploratory Rewards by Embodied Evolution and Constrained Reinforcement Learning in the Cyber Rodents
The aim of the Cyber Rodent project [1] is to elucidate the origin of our reward and affective systems by building artificial agents that share the natural biological constraints...
Eiji Uchibe, Kenji Doya
GECCO
2010
Springer
153views Optimization» more  GECCO 2010»
15 years 27 days ago
Multi-task evolutionary shaping without pre-specified representations
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...
Matthijs Snel, Shimon Whiteson
IWLCS
2005
Springer
15 years 3 months ago
Counter Example for Q-Bucket-Brigade Under Prediction Problem
Aiming to clarify the convergence or divergence conditions for Learning Classifier System (LCS), this paper explores: (1) an extreme condition where the reinforcement process of ...
Atsushi Wada, Keiki Takadama, Katsunori Shimohara
CORR
2002
Springer
100views Education» more  CORR 2002»
14 years 9 months ago
A neural model for multi-expert architectures
We present a generalization of conventional artificial neural networks that allows for a functional equivalence to multi-expert systems. The new model provides an architectural fr...
Marc Toussaint