conftrace_

parameterized policy

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

policy optimization (2) reinforcement learning (2) path integral (1) trajectory rollout (1) belief-state query (1) user alignment (1) stochastic optimal control (1) linear convergence (1) mirror descent (1) partial observability (1)

Papers

Belief-State Query Policies for User-Aligned POMDPs NeurIPS 2024 A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence NeurIPS 2023 Learning Policy Improvements with Path Integrals AISTATS 2010