Introduces a Chebyshev-motivated Bellman operator that provably envelopes and converges to a coverage set of the Pareto frontier in MOMDPs while allowing extraction of deterministic policies for any preference.
Title resolution pending
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
-
Deterministic Pareto-Optimal Policy Synthesis for Multi-Objective Reinforcement Learning
Introduces a Chebyshev-motivated Bellman operator that provably envelopes and converges to a coverage set of the Pareto frontier in MOMDPs while allowing extraction of deterministic policies for any preference.