Login / Signup

Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient.

Kevin Sebastian LuckMel VeceríkSimon StepputtisHeni Ben AmorJonathan Scholz
Published in: IROS (2019)
Keyphrases
  • parametric optimization
  • policy gradient
  • optimization algorithm
  • reinforcement learning
  • optimization problems
  • actor critic
  • optimization methods
  • cost function
  • genetic algorithm
  • path planning
  • latent variables