PackerBot: Variable-Sized Product Packing with Heuristic Deep Reinforcement Learning.
Zifei YangShuo YangShuai SongWei ZhangRan SongJiyu ChengYibin LiPublished in: IROS (2021)
Keyphrases
- variable sized
- reinforcement learning
- packing problem
- dynamic programming
- strip packing
- simulated annealing
- search algorithm
- learning algorithm
- reinforcement learning algorithms
- life cycle
- function approximation
- deep learning
- product development
- action selection
- model free
- optimal policy
- machine learning
- multi agent reinforcement learning
- product information
- optimal solution
- temporal difference
- markov decision processes
- production planning
- combinatorial optimization
- tabu search
- learning problems
- exact algorithms
- multi agent
- heuristic methods
- search procedure
- genetic algorithm
- maximum profit
- neural network