Momentum-based Accelerated Q-learning.
Bowen WengLin ZhaoHuaqing XiongWei ZhangPublished in: CoRR (2019)
Keyphrases
- learning rate
- reinforcement learning
- learning algorithm
- function approximation
- state space
- cooperative
- convergence rate
- multi agent
- action selection
- convergence speed
- reinforcement learning algorithms
- optimal policy
- genetic algorithm
- potential field
- stochastic approximation
- bucket brigade
- e learning
- multi agent reinforcement learning
- temporal difference learning
- stochastic games
- model free
- search engine
- dynamic programming
- support vector