Sub-optimal Policy Aided Multi-Agent Reinforcement Learning for Flocking Control.
Yunbo QiuYue JinJian WangXudong ZhangPublished in: SMC (2022)
Keyphrases
- optimal policy
- multi agent reinforcement learning
- reinforcement learning
- control policies
- markov decision processes
- finite horizon
- state space
- distributed control
- infinite horizon
- decision problems
- long run
- dynamic programming
- finite state
- state dependent
- markov decision process
- control system
- learning agents
- average reward
- multi agent systems
- reward function
- multistage
- multi agent
- learning agent
- stochastic games
- sufficient conditions
- optimal control
- dynamic environments
- cooperative
- policy iteration
- machine learning