most citedImproving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning

2 citations · 2 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2021★ 2 cited

Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning

Bernie Wang, Simon Xu, Kurt Keutzer +2

Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with mo…