Articles under the label of RL

  1. Home
  2. RL

【论文笔记MGRL】UVFA: Universal Value Function Approximators

ICML 2015摘要Value functions are a core component of r...

  • DarkDawn
  • July 26, 2022
  • 2 comments
    •

    【论文笔记MTRL】SM: Multi-Task Reinforcement Learning with Soft Modularization

    NeurIPS 2020摘要Multi-task learning is a very challeng...

  • DarkDawn
  • July 25, 2022
  • 3 comments
    •

    【论文笔记MTRL】GATO: A Generalist Agent

    Deepmind摘要Inspired by progress in large-scale langua...

  • DarkDawn
  • July 20, 2022
  • 1 comments
    •

    【论文笔记 MTRL】CARE: Multi-Task Reinforcement Learning with Context-based Representations

    ICML 2021摘要The benefit of multi-task learning over s...

  • DarkDawn
  • April 29, 2022
  • 2 comments
    •

    【论文笔记 MTRL】PCGrad: Gradient Surgery for Multi-Task Learning

    NeurIPS2020摘要While deep learning and deep reinforcem...

  • DarkDawn
  • April 14, 2022
  • 3 comments