Preference learning for guiding the tree search in continuous POMDPs.
Jiyong AhnSanghyeon SonDongryung LeeJisu HanDongwon SonBeomjoon KimPublished in: CoRL (2023)
Keyphrases
- tree search
- preference learning
- branch and bound
- search algorithm
- ordinal regression
- constraint propagation
- gaussian processes
- pairwise comparison
- state space
- search tree
- reinforcement learning
- mathematical programming
- active learning
- ranking functions
- dynamic programming
- recommender systems
- search space
- upper bound
- constraint programming
- heuristic search
- markov chain
- special case