Establishes stability of belief filters to model error in log-linear and neural-softmax POMDPs under mixing conditions and derives finite-sample guarantees for preference-based reward learning that decouple statistical error from model-mismatch bias.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Preference-Based Reward Learning under Partial Observability with Inexact Dynamics
Establishes stability of belief filters to model error in log-linear and neural-softmax POMDPs under mixing conditions and derives finite-sample guarantees for preference-based reward learning that decouple statistical error from model-mismatch bias.