DeepAI AI Chat
Log In Sign Up

A Novel Framework for Policy Mirror Descent with General Parametrization and Linear Convergence

by   Carlo Alfano, et al.

Modern policy optimization methods in applied reinforcement learning, such as Trust Region Policy Optimization and Policy Mirror Descent, are often based on the policy gradient framework. While theoretical guarantees have been established for this class of algorithms, particularly in the tabular setting, the use of a general parametrization scheme remains mostly unjustified. In this work, we introduce a novel framework for policy optimization based on mirror descent that naturally accommodates general parametrizations. The policy class induced by our scheme recovers known classes, e.g. softmax, and it generates new ones, depending on the choice of the mirror map. For a general mirror map and parametrization class, we establish the quasi-monotonicity of the updates in value function, global linear convergence rates, and we bound the total expected Bregman divergence of the algorithm along its path. To showcase the ability of our framework to accommodate general parametrization schemes, we present a case study involving shallow neural networks.


page 1

page 2

page 3

page 4


On the Convergence Rates of Policy Gradient Methods

We consider infinite-horizon discounted Markov decision problems with fi...

On the Convergence of Policy in Unregularized Policy Mirror Descent

In this short note, we give the convergence analysis of the policy in th...

Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization

We analyze the convergence rate of the unregularized natural policy grad...

Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence

Policy optimization, which learns the policy of interest by maximizing t...

Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies

We consider infinite-horizon discounted Markov decision processes and st...

Neural Temporal-Difference Learning Converges to Global Optima

Temporal-difference learning (TD), coupled with neural networks, is amon...

Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization

We introduce a novel framework for optimization based on energy-conservi...