AET framework unifies SER and ESR criteria for nonlinear MORL; AETDICE enables offline optimization via DICE-style estimation in augmented state space.
On the limitations of markovian rewards to express multi- objective, risk-sensitive, and modal tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RL
AET framework unifies SER and ESR criteria for nonlinear MORL; AETDICE enables offline optimization via DICE-style estimation in augmented state space.