20 citations · 39 across the 9 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021
When should agents explore?
Miruna Pîslar, David Szepesvari, Georg Ostrovski +2
Exploration remains a central challenge for reinforcement learning (RL). Virtually all existing methods share the feature of a monolithic behaviour policy that changes only gradual…
cs.CL2021
Machine Translation Decoding beyond Beam Search
Rémi Leblond, Jean-Baptiste Alayrac, Laurent Sifre +5
Beam search is the go-to method for decoding auto-regressive machine translation models. While it yields consistent improvements in terms of BLEU, it is only concerned with finding…