The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces.
Chi JinQinghua LiuTiancheng YuPublished in: CoRR (2021)
Keyphrases
- multi agent
- reinforcement learning
- state space
- reinforcement learning algorithms
- power consumption
- heuristic search
- optimal policy
- multiagent systems
- multi agent systems
- markov chain
- multiple agents
- learning agents
- multiagent reinforcement learning
- single agent
- function approximation
- multi agent environments
- autonomous agents
- markov decision processes
- planning problems
- intelligent agents
- machine learning
- action space
- cooperative
- control problems
- team formation
- continuous state spaces
- agent based simulations
- agent oriented
- belief state
- temporal difference
- action selection
- learning problems
- software agents
- particle filter
- search algorithm