A dynamic mission abort policy for transportation systems with stochastic dependence by deep reinforcement learning.
Lujie LiuJun YangBingxin YanPublished in: Reliab. Eng. Syst. Saf. (2024)
Keyphrases
- transportation systems
- reinforcement learning
- optimal policy
- control policies
- markov decision processes
- policy search
- model free reinforcement learning
- dynamic environments
- direct policy search
- continuous state spaces
- distributed database systems
- state space
- stochastic approximation
- action space
- policy iteration
- markov decision process
- response time
- partially observable
- reinforcement learning algorithms
- action selection
- model free
- policy gradient
- function approximation
- approximate dynamic programming
- concurrency control
- reinforcement learning problems
- state and action spaces
- natural language processing
- supervised learning