• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Taking complementary advantages: Improving exploration via double self-imitation learning in procedurally-generated environments.

Hao LinYue HeFanzhang LiQuan LiuBangjun WangFei Zhu
Published in: Expert Syst. Appl. (2024)
Keyphrases
  • imitation learning
  • robotic systems
  • maximum margin
  • humanoid robot
  • dynamic environments
  • reinforcement learning
  • video sequences
  • multi modal
  • computer vision
  • state space