LF-IBIS combines Approximate Bayesian Computation with iterated batch importance sampling to perform online, likelihood-free Bayesian reinforcement learning and to place a posterior distribution over optimal policies.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Full Bayesian Reinforcement Learning via LF-IBIS
LF-IBIS combines Approximate Bayesian Computation with iterated batch importance sampling to perform online, likelihood-free Bayesian reinforcement learning and to place a posterior distribution over optimal policies.