Sign in

Improving Sample Efficiency and Multi-Agent Communication in RL-based Train Rescheduling.

Dano RoostRalph MeierStephan HuschauerErik NygrenAdrian EgliAndreas WeilerThilo Stadelmann
Published in: SDS (2020)
Keyphrases
  • agent communication
  • multi agent
  • multi agent systems
  • reinforcement learning
  • cooperative
  • markov decision processes
  • agent architecture
  • case study
  • data collection
  • model free