1. Learning dexterous in-hand manipulation
AndrychowiczM.
BakerB.
ChociejM.
RafalJ.
BobM.
JakubP.
10.48550/arXiv.1808.001772018
2. Hindsight experience replay
AndrychowiczM.
WolskiF.
RayA.
SchneiderJ.
FongR.
WelinderP.
10.48550/arXiv.1707.014952017
3. Deep reinforcement learning: A brief survey;Arulkumaran;IEEE Signal Process. Mag.,2017
4. Agent57: Outperforming the atari human benchmark;Badia
5. Emergent complexity via multi-agent competition
BansalT.
PachockiJ.
SidorS.
SutskeverI.
MordatchI.
10.48550/arXiv.1710.037482017