22 citations · 86 across the 20 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2020★ 1 cited
Multi-agent Policy Optimization with Approximatively Synchronous Advantage Estimation
Lipeng Wan, Xuwei Song, Xuguang Lan +1
Cooperative multi-agent tasks require agents to deduce their own contributions with shared global rewards, known as the challenge of credit assignment. General methods for policy b…
cs.LG2019★ 8 cited
Hindsight Trust Region Policy Optimization
Hanbo Zhang, Site Bai, Xuguang Lan +2
Reinforcement Learning(RL) with sparse rewards is a major challenge. We propose \emph{Hindsight Trust Region Policy Optimization}(HTRPO), a new RL algorithm that extends the highly…