Task Constraint-Guided Inverse Reinforcement Learning (TC-IRL) in Human-Robot Collaborative Assembly.
Yi ChenWeitian WangYunyi JiaPublished in: ARSO (2024)
Keyphrases
- inverse reinforcement learning
- human robot
- bayesian nonparametric
- human robot interaction
- partially observable environments
- dialogue system
- preference elicitation
- reward function
- action selection
- humanoid robot
- robotic systems
- human users
- objective function
- artificial life
- software agents
- natural language
- cooperative
- multi agent