Efficient Reinforcement Learning of Task Planners for Robotic Palletization through Iterative Action Masking Learning.
Zheng WuYichuan LiWei ZhanChangliu LiuYun-Hui LiuMasayoshi TomizukaPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- action selection
- learning systems
- supervised learning
- dynamic programming
- state space
- online learning
- learning tasks
- mobile robot
- neural network
- learning problems
- robot control
- state action
- action models
- actor critic
- imitation learning
- partially observable domains