Diverse Exploration via Conjugate Policies for Policy Gradient Methods

Understand

We address the challenge of effective exploration while maintaining good performance in policy gradient methods.

• As a solution, we propose diverse exploration (DE) via conjugate policies.
• DE learns and deploys a set of conjugate policies which can be conveniently generated as a byproduct of conjugate gradient descent.
• We provide both theoretical and empirical results showing the effectiveness of DE at achieving exploration, improving policy performance, and the advantage of DE over exploration by random policy perturbations.