3274 search results - page 340 / 655 » Using Learning in a Control Agent |
179
Voted
ICML
2006
IEEE
16 years 7 months ago
2006
IEEE
Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms co...
207
Voted
ML
2007
ACM
15 years 6 months ago
2007
ACM
We offer a new formal criterion for agent-centric learning in multi-agent systems, that is, learning that maximizes one’s rewards in the presence of other agents who might also...
156
click to vote
ICML
2006
IEEE
16 years 7 months ago
2006
IEEE
We introduce the controlled predictive linearGaussian model (cPLG), a model that uses predictive state to model discrete-time dynamical systems with real-valued observations and v...
134
click to vote
AR
2002
15 years 6 months ago
2002
: This paper deals with twisting motion of a falling cat robot by two torque inputs around her waist. The cat robot consists of two rigid columns and has internally two actuators a...
184
click to vote
IROS
2007
IEEE
16 years 29 days ago
2007
IEEE
— While underactuated robotic systems are capable of energy efficient and rapid dynamic behavior, we still do not fully understand how body dynamics can be actively used for ada...