Login / Signup

Value Function Decomposition for Iterative Design of Reinforcement Learning Agents.

James MacGlashanEvan ArcherAlisa DevlicTakuma SenoCraig SherstanPeter R. WurmanPeter Stone
Published in: CoRR (2022)
Keyphrases
  • reinforcement learning agents
  • data sets
  • genetic algorithm
  • probability distribution
  • hierarchical decomposition