Optimization step in Apprenticeship Learning via Inverse Reinforcement Learning

Ask Question

Asked 2 years, 8 months ago

Active 2 years, 8 months ago

Viewed 53 times

Why the optimization step of the algorithm a quadratic program? [See: Apprenticeship Learning via Inverse Reinforcement Learning; page 3]

Isn't the objective function linear? Why don't we treat the problem as LPQC (linear program with quadratic constraints)?

DukeZhou♦

6,0704 gold badges19 silver badges46 bronze badges

asked Aug 8 '18 at 5:16

İbrahim Abbasov

511 bronze badge

1

$\begingroup$ Could you perhaps include a link to a relevant paper? It looks like you have a very specific algorithm in mind, and if you can link to it, others will be better able to help. $\endgroup$ – John Doucette♦ Aug 8 '18 at 7:55
1

$\begingroup$ ai.stanford.edu/~ang/papers/icml04-apprentice.pdf $\endgroup$ – İbrahim Abbasov Aug 8 '18 at 8:22
$\begingroup$ the algorithm is in the 3rd page $\endgroup$ – İbrahim Abbasov Aug 8 '18 at 8:23

Add a comment |

0 Your Answer

Name

Required, but never shown

Post as a guest

Name

Required, but never shown

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy