The　safe　and　reliable　operation　of　power　grid　equipment　is　the　basis　for　ensuring　the　safe　operation　of　the　power　system.　At　present,　the　traditional　periodical　maintenance　has　exposed　the　abuses　such　as　deficient　maintenance　and　excess　maintenance.　Based　on　a　multiagent　deep　reinforcement　learning　decision-making　optimization　algorithm,　a　method　for　decision-making　and　optimization　of　power　grid　equipment　maintenance　plans　is　proposed.　In　this　paper,　an　optimization　model　of　power　grid　equipment　maintenance　plan　that　takes　into　account　the　reliability　and　economics　of　power　grid　operation　is　constructed　with　maintenance　constraints　and　power　grid　safety　constraints　as　its　constraints.　The　deep　distributed　recurrent　Q-networks　multiagent　deep　reinforcement　learning　is　adopted　to　solve　the　optimization　model.　The　deep　distributed　recurrent　Q-networks　multiagent　deep　reinforcement　learning　uses　the　high-dimensional　feature　extraction　capabilities　of　deep　learning　and　decision-making　capabilities　of　reinforcement　learning　to　solve　the　multiobjective　decision-making　problem　of　power　grid　maintenance　planning.　Through　case　analysis,　the　comparative　results　show　that　the　proposed　algorithm　has　better　optimization　and　decision-making　ability,　as　well　as　lower　maintenance　cost.　Accordingly,　the　algorithm　can　realize　the　optimal　decision　of　power　grid　equipment　maintenance　plan.　The　expected　value　of　power　shortage　and　maintenance　cost　obtained　by　the　proposed　method　is　$71.75$　$MW.H$　and　$496000$　$yuan$.