48 citations · 85 across the 9 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.RO2019
Risk-Averse Planning Under Uncertainty
Mohamadreza Ahmadi, Masahiro Ono, Michel D. Ingham +2
We consider the problem of designing policies for partially observable Markov decision processes (POMDPs) with dynamic coherent risk objectives. Synthesizing risk-averse optimal po…
cs.LG2019★ 3 cited
Co-training for Policy Learning
Jialin Song, Ravi Lanka, Yisong Yue +1
We study the problem of learning sequential decision-making policies in settings with multiple state-action representations. Such settings naturally arise in many domains, such as…