Developing　a　safe　and　efficient　collision-avoidance　policy　for　multiple　robots　is　challenging　in　the　decentralized　scenarios　where　each　robot　generates　its　paths　with　limited　observation　of　other　robots＇　states　and　intentions.　Prior　distributed　multi-robot　collision-avoidance　systems　often　require　frequent　inter-robot　communication　or　agent-level　features　to　plan　a　local　collision-free　action,　which　is　not　robust　and　computationally　prohibitive.　In　addition,　the　performance　of　these　methods　is　not　comparable　with　their　centralized　counterparts　in　practice.　In　this　article,　we　present　a　decentralized　sensor-level　collision-avoidance　policy　for　multi-robot　systems,　which　shows　promising　results　in　practical　applications.　In　particular,　our　policy　directly　maps　raw　sensor　measurements　to　an　agent＇s　steering　commands　in　terms　of　the　movement　velocity.　As　a　first　step　toward　reducing　the　performance　gap　between　decentralized　and　centralized　methods,　we　present　a　multi-scenario　multi-stage　training　framework　to　learn　an　optimal　policy.　The　policy　is　trained　over　a　large　number　of　robots　in　rich,　complex　environments　simultaneously　using　a　policy-gradient-based　reinforcement-learning　algorithm.　The　learning　algorithm　is　also　integrated　into　a　hybrid　control　framework　to　further　improve　the　policy＇s　robustness　and　effectiveness.　We　validate　the　learned　sensor-level　collision-3avoidance　policy　in　a　variety　of　simulated　and　real-world　scenarios　with　thorough　performance　evaluations　for　large-scale　multi-robot　systems.　The　generalization　of　the　learned　policy　is　verified　in　a　set　of　unseen　scenarios　including　the　navigation　of　a　group　of　heterogeneous　robots　and　a　large-scale　scenario　with　100　robots.　Although　the　policy　is　trained　using　simulation　data　only,　we　have　successfully　deployed　it　on　physical　robots　with　shapes　and　dynamics　characteristics　that　are　different　from　the　simulated　agents,　in　order　to　demonstrate　the　controller＇s　robustness　against　the　simulation-to-real　modeling　error.　Finally,　we　show　that　the　collision-avoidance　policy　learned　from　multi-robot　navigation　tasks　provides　an　excellent　solution　for　safe　and　effective　autonomous　navigation　for　a　single　robot　working　in　a　dense　real　human　crowd.　Our　learned　policy　enables　a　robot　to　make　effective　progress　in　a　crowd　without　getting　stuck.　More　importantly,　the　policy　has　been　successfully　deployed　on　different　types　of　physical　robot　platforms　without　tedious　parameter　tuning.　Videos　are　available　at　.