Login / Signup

Safe- to-Explore State Spaces: Ensuring Safe Exploration in Policy Search with Hierarchical Task Optimization.

Jens LundellRobert KrugErik SchaffernichtTodor StoyanovVille Kyrki
Published in: Humanoids (2018)
Keyphrases
  • policy search
  • state space
  • reinforcement learning
  • reinforcement learning algorithms
  • neural network
  • multi agent
  • dynamic programming
  • markov chain
  • dynamic environments
  • continuous state