JMLR · @jmlr
714 followers · 323 posts · Server sigmoid.social

'Q-Learning for MDPs with General Spaces: Convergence and Near Optimality via Quantization under Weak Continuity', by Ali Kara, Naci Saldi, Serdar YĆ¼ksel.

jmlr.org/papers/v24/21-1457.ht

#quantization #quantized #mdps

Last updated 1 year ago

JMLR · @jmlr
653 followers · 179 posts · Server sigmoid.social

'Provably Sample-Efficient Model-Free Algorithm for MDPs with Peak Constraints', by Qinbo Bai, Vaneet Aggarwal, Ather Gattami.

jmlr.org/papers/v24/21-0117.ht

#mdps #markov #pcmdp

Last updated 1 year ago