Curriculum Reinforcement Learning From Avoiding Collisions to Navigating Among Movable Obstacles in Diverse Environments.
Hsueh-Cheng WangSiao-Cing HuangPo-Jui HuangKuo-Lun WangYi-Chen TengYu-Ting KoDongsuk JeonI-Chen WuPublished in: IEEE Robotics Autom. Lett. (2023)
Keyphrases
- reinforcement learning
- function approximation
- real world
- wide variety
- collision free
- reinforcement learning algorithms
- dynamic environments
- machine learning
- model free
- action selection
- state space
- multi agent
- markov decision processes
- autonomous robot navigation
- free space
- markov decision process
- data sets
- complex environments
- path planning
- supervised learning
- software engineering
- learning algorithm