trends.barnas.net

method · first seen 6 Oct 2026

entropy regularization

Adding an entropy bonus to the RL objective to encourage exploration and prevent policy collapse.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

offline reinforcement learningadjoint matchinggroup relative policy optimizationmulti-agent reinforcement learningdecentralized actor-critic