conftrace_

constraint markov decision process

1 paper

Explore in graph

Also known as

CMDP

Co-occurring keywords · papers mentioning both

convex mdp (1) partial data coverage (1) primal-dual method (1) safe reinforcement learning (1) primal-dual algorithm (1) linear programming (1) sample complexity (1) convex optimization (1) offline reinforcement learning (1)

Papers

Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage NeurIPS 2024