V-Learning - A Simple, Efficient, Decentralized Algorithm for Multiagent RL.
Chi JinQinghua LiuYuanhao WangTiancheng YuPublished in: CoRR (2021)
Keyphrases
- learning algorithm
- multi agent
- reinforcement learning
- learning tasks
- learning process
- preprocessing
- incremental learning
- detection algorithm
- single pass
- model free
- worst case
- learning problems
- computationally efficient
- dynamic programming
- high efficiency
- np hard
- learning phase
- machine learning
- learning agents
- temporal difference learning
- image restoration
- distributed systems
- cost function
- optimal solution
- objective function
- similarity measure
- genetic algorithm