conftrace_

general policy improvement

1 paper

Explore in graph

Also known as

GPI

Co-occurring keywords · papers mentioning both

trust-region learning (1) mirror learning (1) policy optimisation (1) theoretical framework (1) trust region optimization (1) policy improvement (1) policy optimization (1) deep reinforcement learning (1)

Papers

Mirror Learning: A Unifying Framework of Policy Optimisation ICML 2022