Autoregressive Policy Optimization for Constrained Allocation Tasks

TL;DR

This paper introduces an autoregressive policy optimization method for constrained allocation tasks, effectively handling linear constraints and outperforming existing constrained reinforcement learning approaches across multiple domains.

Contribution

The paper presents a novel autoregressive sampling approach with a de-biasing mechanism for constrained allocation, advancing the capabilities of reinforcement learning in complex constrained environments.

Findings

Outperforms existing CRL methods on portfolio optimization

Effective in workload distribution tasks

Demonstrates robustness on synthetic benchmarks

Abstract

Allocation tasks represent a class of problems where a limited amount of resources must be allocated to a set of entities at each time step. Prominent examples of this task include portfolio optimization or distributing computational workloads across servers. Allocation tasks are typically bound by linear constraints describing practical requirements that have to be strictly fulfilled at all times. In portfolio optimization, for example, investors may be obligated to allocate less than 30\% of the funds into a certain industrial sector in any investment period. Such constraints restrict the action space of allowed allocations in intricate ways, which makes learning a policy that avoids constraint violations difficult. In this paper, we propose a new method for constrained allocation tasks based on an autoregressive process to sequentially sample allocations for each entity. In addition, we introduce a novel de-biasing mechanism to counter the initial bias caused by sequential sampling. We demonstrate the superior performance of our approach compared to a variety of Constrained Reinforcement Learning (CRL) methods on three distinct constrained allocation tasks: portfolio optimization, computational workload distribution, and a synthetic allocation benchmark. Our code is available at: https://github.com/niklasdbs/paspo