109 search results - page 6 / 22 » Policy teaching through reward function learning |
ICML
2000
IEEE
14 years 8 months ago
2000
IEEE
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
COLT
2007
Springer
14 years 1 months ago
2007
Springer
Bounded parameter Markov Decision Processes (BMDPs) address the issue of dealing with uncertainty in the parameters of a Markov Decision Process (MDP). Unlike the case of an MDP, t...
CDC
2008
IEEE
14 years 2 months ago
2008
IEEE
—We consider a multiarmed bandit problem where the expected reward of each arm is a linear function of an unknown scalar with a prior distribution. The objective is to choose a s...
ICML
1997
IEEE
14 years 8 months ago
1997
IEEE
The goal of robot learning from demonstration is to have a robot learn from watching a demonstration of the task to be performed. In our approach to learning from demonstration th...
UAI
2008
13 years 9 months ago
2008
An efficient policy search algorithm should estimate the local gradient of the objective function, with respect to the policy parameters, from as few trials as possible. Whereas m...