Given　the　popularity　of　flawless　telepresence　and　the　resultants　explosive　growth　of　wireless　video　applications,　besides　handling　the　traffic　surge,　satisfying　the　demanding　user　requirements　for　video　qualities　has　become　another　important　goal　of　network　operators.　Inspired　by　this,　cooperative　edge　caching　intrinsically　amalgamated　with　scalable　video　coding　is　investigated.　Explicitly,　the　concept　of　a　Pareto-optimal　semi-distributed　multi-agent　multi-policy　deep　reinforcement　learning　(SD-MAMP-DRL)　algorithm　is　conceived　for　managing　the　cooperation　of　heterogeneous　network　nodes.　To　elaborate,　a　multi-policy　reinforcement　learning　algorithm　is　proposed　for　finding　the　Pareto-optimal　policies　during　the　training　phase,　which　balances　the　tele-traffic　vs.　the　user　experience　trade-off.　Then　the　optimal　policy/solution　can　be　activated　during　the　execution　phase　by　appropriately　selecting　the　associated　weighting　coefficient　according　to　the　dynamically　fluctuating　network　traffic　load.　Our　experimental　results　show　that　the　proposed　SD-MAMP-DRL　algorithm　1)　achieves　better　performance　than　the　benchmark　algorithms;　2)　obtains　a　near-complete　Pareto-front　in　various　scenarios　and　selects　the　optimal　solution　by　adaptively　adjusting　the　above-mentioned　pair　of　objectives.　IEEE