Explaining Reward Functions to Humans for Better Human-Robot Collaboration.
Lindsay SannemanJulie ShahPublished in: CoRR (2021)
Keyphrases
- human robot
- reward function
- human users
- human robot interaction
- dialogue system
- markov decision processes
- reinforcement learning
- state space
- inverse reinforcement learning
- multiple agents
- humanoid robot
- action selection
- transition probabilities
- robotic systems
- state variables
- policy search
- optimal policy
- multi modal
- human subjects
- intelligent agents
- generative model