Login / Signup

A History-based Framework for Online Continuous Action Ensembles in Deep Reinforcement Learning.

Renata Garcia OliveiraWouter Caarls
Published in: ICAART (2) (2021)
Keyphrases
  • reinforcement learning
  • policy search
  • multi agent
  • search algorithm
  • computational complexity
  • markov decision processes
  • machine learning
  • learning algorithm
  • function approximation
  • continuous state
  • continuous action