Login / Signup

Stable and Efficient Shapley Value-Based Reward Reallocation for Multi-Agent Reinforcement Learning of Autonomous Vehicles.

Songyang HanHe WangSanbao SuYuanyuan ShiFei Miao
Published in: ICRA (2022)
Keyphrases
  • multi agent reinforcement learning
  • autonomous vehicles
  • structured environments
  • real time
  • reinforcement learning
  • multi agent
  • path planning
  • obstacle avoidance
  • multi agent learning