Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning.
Hadi NekoeiAkilesh BadrinaaraayananAmit SinhaMohammad AminiJanarthanan RajendranAditya MahajanSarath ChandarPublished in: CoLLAs (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- supervised learning
- knowledge acquisition
- evolutionary learning
- prior knowledge
- learning capabilities
- peer to peer
- cooperative multi agent
- action selection
- learning classifier systems
- learning problems
- learning tasks
- online learning
- active learning
- cooperative
- multi agent
- learning systems
- non stationary
- state space
- reinforcement learning methods
- rl algorithms
- multi agent reinforcement learning
- active exploration