Maximum-Diffusion Reinforcement Learner@MaxDiffusionRL

Replying to @parafactual

@parafactual @tenobrus @sigfig @bmorphism @Stugs @Irischaser @amplifiedamp @exdiegesis @calithameridi @np_eazy @AbstractRevery @adrusi @sanjehorah @repligate @anthrupad @TomboyTesting @algekalipso @fiorosebloom @modaminister @NonameNemo8 @alexeyguzey