Cooperative modular reinforcement learning for large discrete action space problem.
Fangzhu MingFeng GaoKun LiuChengmei ZhaoPublished in: Neural Networks (2023)
Keyphrases
- action space
- reinforcement learning
- cooperative
- continuous state
- continuous state spaces
- continuous action
- state space
- markov decision processes
- state and action spaces
- real valued
- stochastic processes
- reinforcement learning methods
- multi agent
- control policies
- action selection
- state action
- policy search
- reinforcement learning algorithms
- single agent
- control problems
- optimal policy
- dynamic programming
- function approximators
- machine learning
- finite number
- temporal difference
- multi agent systems
- search algorithm
- learning algorithm