87 search results - page 10 / 18 » Hybrid Least-Squares Algorithms for Approximate Policy Evalu... |
ICML
2008
IEEE
14 years 8 months ago
2008
IEEE
Residual gradient (RG) was proposed as an alternative to TD(0) for policy evaluation when function approximation is used, but there exists little formal analysis comparing them ex...
ATAL
2009
Springer
14 years 2 months ago
2009
Springer
Reinforcement learning algorithms that use eligibility traces, such as Sarsa(λ), have been empirically shown to be effective in learning good estimated-state-based policies in pa...
SIGMETRICS
2005
ACM
14 years 1 months ago
2005
ACM
We define the class of SMART scheduling policies. These are policies that bias towards jobs with small remaining service times, jobs with small original sizes, or both, with the ...
ICRA
2010
IEEE
13 years 6 months ago
2010
IEEE
Abstract— We propose a planning algorithm that allows usersupplied domain knowledge to be exploited in the synthesis of information feedback policies for systems modeled as parti...
RSS
2007
13 years 9 months ago
2007
Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...