conftrace_

pessimistic dual value iteration

1 paper

Explore in graph

Also known as

PEDI

Co-occurring keywords · papers mentioning both

dual gradient ascent (1) pessimistic optimization (1) multi-objective optimization (1) linear function approximation (1) constrained optimization (1) function approximation (1) offline reinforcement learning (1)

Papers

Offline Constrained Multi-Objective Reinforcement Learning via Pessimistic Dual Value Iteration NeurIPS 2021