3274 search results - page 33 / 655 » Using Learning in a Control Agent |
ATAL
2006
Springer
13 years 11 months ago
2006
Springer
The "ZIP" adaptive trading algorithm has been demonstrated to outperform human traders in experimental studies of continuous double auction (CDA) markets. The original Z...
CORR
2010
Springer
13 years 5 months ago
2010
Springer
This paper asks a new question: how can we control the collective behavior of self-organized multi-agent systems? We try to answer the question by proposing a new notion called `So...
ATAL
2006
Springer
13 years 11 months ago
2006
Springer
This paper examines agent-based systems designed for a variety of human learning tasks. These are typically split into two areas: "training", which generally refers to a...
ESSMAC
2003
Springer
14 years 29 days ago
2003
Springer
Abstract. Gaussian process models provide a probabilistic non-parametric modelling approach for black-box identification of nonlinear dynamic systems. The Gaussian processes can h...
ICML
1998
IEEE
13 years 12 months ago
1998
IEEE
We present and solve a real-world problem of learning to drive a bicycle. We solve the problem by online reinforcement learning using the Sarsa( )-algorithm. Then we solve the ...