DarkDawn

Welcome to DarkDawn's Blog!

置顶【论文笔记】汇总

多任务强化学习 Multi-Task RLGradientPCGrad: Gradient Surger...

  • DarkDawn
  • July 21, 2022
  • 7 comments
    •

    【论文笔记MTRL】CAMRL: Curriculum-based Asymmetric Multi-task Reinforcement Learning

    TPAMI摘要We introduce CAMRL, the first curriculum-base...

  • DarkDawn
  • December 25, 2022
  • 9 comments
    •

    【论文笔记MTRL】Uni[MASK]: Unified Inference in Sequential Decision Problems

    NeurIPS 2022摘要Randomly masking and predicting word t...

  • DarkDawn
  • December 25, 2022
  • 7 comments
    •

    【论文笔记MTRL】PaCo: Parameter-Compositional Multi-Task Reinforcement Learning

    NeurIPS 2022摘要The purpose of multi-task reinforcemen...

  • DarkDawn
  • December 18, 2022
  • 8 comments
    •

    【论文笔记MTRL】In-context Reinforcement Learning with Algorithm Distillation

    DeepMind摘要We propose Algorithm Distillation (AD), a ...

  • DarkDawn
  • December 14, 2022
  • 12 comments
    •

    【论文笔记MTRL】Routing Networks: Adaptive selection of non-linear functions for multi-task learning

    ICLR 2018本文严格意义是MTL，而非MTRL摘要Multi-task learning (MTL...

  • DarkDawn
  • August 11, 2022
  • 1 comments