conftrace_

projected policy gradient

2 papers

Explore in graph

Also known as

PPG

Co-occurring keywords · papers mentioning both

convergence analysis (2) adaptive tolerance (1) robust average-reward mdps (1) transition evaluation (1) sublinear convergence (1) step size (1) policy iteration (1) policy gradient (1) reinforcement learning (1)

Papers

On the Convergence of Projected Policy Gradient for Any Constant Step Sizes JMLR 2025 Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity ICML 2025