Reinforcement learning for disassembly sequence planning optimization.
Amal AllaguiImen BelhadjRégis PlateauxMoncef HammadiOlivia PenasNizar AifaouiPublished in: Comput. Ind. (2023)
Keyphrases
- reinforcement learning
- action selection
- optimization algorithm
- multi agent
- macro actions
- hidden state
- markov decision processes
- reward shaping
- global optimization
- function approximation
- single agent
- partially observable
- complex domains
- partially observable domains
- machine learning
- action space
- reinforcement learning algorithms
- optimization process
- heuristic search
- optimal policy
- decision support
- hidden markov models