3250 search results - page 331 / 650 » Parameterized Learning Complexity |
153
click to vote
NIPS
2008
15 years 6 months ago
2008
In this paper we consider approximate policy-iteration-based reinforcement learning algorithms. In order to implement a flexible function approximation scheme we propose the use o...
148
click to vote
PAKM
2004
15 years 6 months ago
2004
Current technology has disappointed many users of cooperative learning environments by its complexity and only slow and tough adaptability to specific users' requirements. In ...
165
Voted
ESANN
2000
15 years 6 months ago
2000
Abstract. For a network of spiking neurons with reasonable postsynaptic potentials, we derive a supervised learning rule akin to traditional error-back-propagation, SpikeProp and s...
163
click to vote
AAAI
2010
15 years 6 months ago
2010
Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes...
155
click to vote
GECCO
2008
Springer
15 years 6 months ago
2008
Springer
The evolution strategy is one of the strongest evolutionary algorithms for optimizing real-value vectors. In this paper, we study how to use it for the evolution of prediction wei...