65 search results - page 7 / 13 » Gradient Descent for General Reinforcement Learning |
142
click to vote
GECCO
2009
Springer
14 years 11 months ago
2009
Springer
The covariance matrix adaptation evolution strategy (CMAES) has proven to be a powerful method for reinforcement learning (RL). Recently, the CMA-ES has been augmented with an ada...
123
click to vote
ICML
2004
IEEE
16 years 2 months ago
2004
IEEE
Synchronous reinforcement learning (RL) algorithms with linear function approximation are representable as inhomogeneous matrix iterations of a special form (Schoknecht & Merk...
145
click to vote
IWLCS
2005
Springer
15 years 7 months ago
2005
Springer
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 ...
110
Voted
CORR
2011
Springer
14 years 5 months ago
2011
Springer
Boosting is a popular way to derive powerful learners from simpler hypothesis classes. Following previous work (Mason et al., 1999; Friedman, 2000) on general boosting frameworks,...
122
click to vote
CORR
2002
Springer
15 years 1 months ago
2002
Springer
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...