trends.barnas.net

method · first seen 7 Oct 2026

average-reward reinforcement learning

Reinforcement learning that optimizes long-run average reward per step rather than discounted return.

Mentions per week

0319 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

multichain Markov decision processQ-learningmaximum-entropy reinforcement learningmean-field gamelifelong multi-agent path findingoptions frameworkpolicy identification