Partial Consistency for Stabilizing Undiscounted Reinforcement Learning.
Haichuan GaoZhile YangTian TanTianren ZhangJinsheng RenPengfei SunShangqi GuoFeng ChenPublished in: IEEE Trans. Neural Networks Learn. Syst. (2023)
Keyphrases
- reinforcement learning
- markov decision processes
- policy iteration
- markov decision problems
- average reward
- state space
- consistency checking
- function approximation
- partially observable
- dynamic programming
- reinforcement learning algorithms
- neural network
- optimal policy
- optimal control
- model free
- multi agent
- markov decision process
- stochastic games
- learning problems
- temporal difference
- average cost
- action space
- learning algorithm
- reinforcement learning methods
- robotic control
- maintaining arc consistency
- transfer learning
- dynamic environments
- objective function
- machine learning