Preference Elicitation for Offline Reinforcement Learning.
Alizée PaceBernhard SchölkopfGunnar RätschGiorgia RamponiPublished in: CoRR (2024)
Keyphrases
- preference elicitation
- reinforcement learning
- utility function
- inverse reinforcement learning
- minimax regret
- multi criteria
- decision theory
- learning algorithm
- state space
- reward function
- machine learning
- model free
- multi attribute
- multi agent
- decision makers
- multiple agents
- combinatorial auctions
- neural network
- function approximation
- markov decision processes
- temporal difference
- preference relations
- single agent
- data mining