Graph-based reinforcement learning for discrete cross-section optimization of planar steel frames.
Kazuki HayashiMakoto OhsakiPublished in: Adv. Eng. Informatics (2022)
Keyphrases
- cross section
- reinforcement learning
- cross sections
- cross sectional
- optimization algorithm
- continuous optimization
- state space
- optimization problems
- decision variables
- continuous state spaces
- learning algorithm
- function approximation
- optimal control
- markov decision processes
- optimal policy
- lagrange multipliers
- semi supervised
- dynamic programming
- continuous state
- moving objects