Preference elicitation and inverse reinforcement learning thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Preference elicitation and inverse reinforcement learning

Published on Nov 30, 20113290 Views

We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous work on Bayesian inve

Related categories

Chapter list

Preference Elicitation and Inverse Reinforcement Learning00:00
Inverse Reinforcement Learning Problem00:00
Preference Elicitation00:38
Inverse Reinforcement Learning01:37
Formalization02:34
Statistical Model04:01
Inference05:42
An MCMC Procedure Inference06:23
MH sampler07:29
Gibbs sampler08:29
Empirical Evaluation09:07
Experimental Results -110:34
Experimental Results - 212:13
Conclusion12:54
Thanks13:42