Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning.
Valerie ChenAbhinav GuptaKenneth MarinoPublished in: ICLR (2021)
Keyphrases
- reinforcement learning
- human subjects
- human behavior
- human beings
- function approximation
- artificial agents
- human centric
- human knowledge
- markov decision processes
- human interaction
- human intelligence
- human users
- human behaviour
- artificial systems
- motion capture
- machine learning
- state space
- decision making
- learning algorithm
- genetic algorithm