121 search results - page 1 / 25 » Toward Off-Policy Learning Control with Function Approximati... |
ICML
2010
IEEE
13 years 5 months ago
2010
IEEE
We present the first temporal-difference learning algorithm for off-policy control with unrestricted linear function approximation whose per-time-step complexity is linear in the ...
ICML
2001
IEEE
14 years 5 months ago
2001
IEEE
We introduce the first algorithm for off-policy temporal-difference learning that is stable with linear function approximation. Off-policy learning is of interest because it forms...
NIPS
2001
13 years 6 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
NN
2010
Springer
12 years 11 months ago
2010
Springer
Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning. In this paper, we first show that the least-squares ...
GECCO
2006
Springer
13 years 8 months ago
2006
Springer
Recently, studies with the XCS classifier system on Boolean functions have shown that in certain types of functions simple crossover operators can lead to disruption and, conseque...