Wanming Yu

Aug 21, 2023 | nature.com | Wanming Yu |Auke Ijspeert |Christopher McGreavy |Eleftherios Triantafyllidis |Guillaume Bellegarda

AbstractRobot motor skills can be acquired by deep reinforcement learning as neural networks to reflect state–action mapping. The selection of states has been demonstrated to be crucial for successful robot motor learning. However, because of the complexity of neural networks, human insights and engineering efforts are often required to select appropriate states through qualitative approaches, such as ablation studies, without a quantitative analysis of the state importance.