Optimization of a Deep Reinforcement Learning Policy for Construction Manufacturing Control.
Ian FloodXiaoyan ZhouPublished in: SIMULTECH (2023)
Keyphrases
- reinforcement learning
- control policy
- control policies
- optimal policy
- control problems
- action selection
- optimal control
- markov decision process
- policy search
- control system
- reward function
- optimization algorithm
- optimization problems
- function approximation
- partially observable
- adaptive control
- long run
- quality control
- robot control
- robotic control
- raw material
- machine learning
- stochastic control
- state space
- partially observable environments
- reinforcement learning problems
- continuous state spaces
- continuous state
- temporal difference
- rl algorithms
- function approximators
- control strategies
- optimization method
- markov decision processes
- dynamic programming
- genetic algorithm