44 citations
- Tsinghua UniversityCN4 papers
- Huazhong University of Science and TechnologyCN3 papers
- Chinese Academy of SciencesCN2 papers
- Institute of AutomationCN2 papers
- Nanjing UniversityCN2 papers
- Beijing University of Posts and TelecommunicationsCN1 paper
- Central South UniversityCN1 paper
- Chinese University of Hong KongHK1 paper
- Horizon Research (United States)US1 paper
- Institute of AcousticsCN1 paper
- Ludwig-Maximilians-Universität MünchenDE1 paper
- Peking UniversityCN1 paper
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021★ 3 cited
Mutual Information State Intrinsic Control
Rui Zhao, Yang Gao, Pieter Abbeel +2
Reinforcement learning has been shown to be highly successful at many challenging tasks. However, success heavily relies on well-shaped rewards. Intrinsically motivated RL attempts…
cs.LG2021★ 44 cited
Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective
Helong Zhou, Liangchen Song, Jiajie Chen +4
Knowledge distillation is an effective approach to leverage a well-trained network or an ensemble of them, named as the teacher, to guide the training of a student network. The out…