Deep Reinforcement Learning Bearing Fault Diagnosis Method Based on Improved Reward Function.
Xinna MaQinqing LiuXuepeng ZhengYu TangYiyang LiXiu LiangPublished in: ISCSIC (2023)
Keyphrases
- reward function
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- state space
- optimal policy
- partially observable
- inverse reinforcement learning
- policy search
- transition model
- hierarchical reinforcement learning
- markov decision process
- multiple agents
- state variables
- learning agent
- average reward
- action selection
- action space
- initially unknown
- model free
- function approximation
- generative model
- data mining
- transition probabilities
- function approximators
- state action
- markov decision problems
- markov chain
- dynamic programming
- hidden markov models
- k means
- machine learning