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: CoRR (2023)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- learning problems
- state space
- active learning
- prior knowledge
- supervised learning
- function approximation
- learning tasks
- learning systems
- temporal difference
- machine learning
- action selection
- markov decision processes
- non stationary
- unsupervised learning
- knowledge acquisition
- distributed systems
- general purpose
- natural language
- cooperative