Low-Cost Multi-Agent Navigation via Reinforcement Learning With Multi-Fidelity Simulator.
Jiantao QiuChao YuWeiling LiuTianxiang YangJincheng YuYu WangHuazhong YangPublished in: IEEE Access (2021)
Keyphrases
- reinforcement learning
- multi agent
- low cost
- function approximation
- cooperative
- multi agent systems
- state space
- multi agent environments
- real robot
- temporal difference
- reinforcement learning agents
- real time
- learning agents
- optimal policy
- multi agent reinforcement learning
- machine learning
- intelligent agents
- visual quality
- reinforcement learning algorithms
- digital camera
- low power
- model free
- cognitive agents
- markov decision process
- agent oriented
- single agent
- simulation model
- information space
- multiple agents
- optimal control
- test bed
- markov decision processes
- multiagent systems
- supervised learning
- learning algorithm
- neural network