TAP-Net: Transport-and-Pack using Reinforcement Learning.
Ruizhen HuJuzhan XuBin ChenMinglun GongHao ZhangHui HuangPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- markov decision processes
- packing problem
- state space
- machine learning
- robotic control
- reinforcement learning algorithms
- model free
- optimal policy
- learning algorithm
- data sets
- supervised learning
- dynamic programming
- learning process
- genetic algorithm
- control problems
- action space
- transfer learning
- optimal control
- evolutionary algorithm
- robot control
- temporal difference learning
- transition model
- direct policy search