IQ-Learn: Inversesoft-QLearningfor Imitation
–Neural Information Processing Systems
J (Q)= E E[ (Q(s, a) Es0 P( |s,a)V (s0))] (1 )E 0[V (s0)], (9) withV (s) = log P aexpQ(s, a).
Neural Information Processing Systems
Feb-7-2026, 19:42:58 GMT
- Country:
- Europe > France
- Auvergne-Rhône-Alpes > Isère > Grenoble (0.04)
- North America > United States
- California > Santa Clara County > Palo Alto (0.04)
- Europe > France
- Technology: