Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published December 2019 | Submitted + Published + Supplemental Material
Book Section - Chapter Open

Imitation-Projected Policy Gradient for Programmatic Reinforcement Learning

Abstract

We study the problem of programmatic reinforcement learning, in which policies are represented as short programs in a symbolic language. Programmatic policies can be more interpretable, generalizable, and amenable to formal verification than neural policies; however, designing rigorous learning approaches for such policies remains a challenge. Our approach to this challenge - a meta-algorithm called PROPEL - is based on three insights. First, we view our learning task as optimization in policy space, modulo the constraint that the desired policy has a programmatic representation, and solve this optimization problem using a form of mirror descent that takes a gradient step into the unconstrained policy space and then projects back onto the constrained space. Second, we view the unconstrained policy space as mixing neural and programmatic representations, which enables employing state-of-the-art deep policy gradient approaches. Third, we cast the projection step as program synthesis via imitation learning, and exploit contemporary combinatorial methods for this task. We present theoretical convergence results for PROPEL and empirically evaluate the approach in three continuous control domains. The experiments show that PROPEL can significantly outperform state-of-the-art approaches for learning programmatic policies.

Additional Information

© 2019 Neural Information Processing Systems Foundation, Inc. This work was supported in part by United States Air Force Contract # FA8750-19-C-0092, NSF Award # 1645832, NSF Award # CCF-1704883, the Okawa Foundation, Raytheon, PIMCO, and Intel.

Attached Files

Published - 9705-imitation-projected-programmatic-reinforcement-learning.pdf

Submitted - 1907.05431.pdf

Supplemental Material - 9705-imitation-projected-programmatic-reinforcement-learning-supplemental.zip

Files

9705-imitation-projected-programmatic-reinforcement-learning-supplemental.zip
Files (2.2 MB)

Additional details

Created:
August 19, 2023
Modified:
October 18, 2023