A generalized algorithm for multi-objective reinforcement learning and policy adaptation

TY - JOUR

T1 - A generalized algorithm for multi-objective reinforcement learning and policy adaptation

AU - Yang, Runzhe

AU - Sun, Xingyuan

AU - Narasimhan, Karthik

N1 - Publisher Copyright: © 2019 Neural information processing systems foundation. All rights reserved.

PY - 2019

Y1 - 2019

N2 - We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks. In MORL, the aim is to learn policies over multiple competing objectives whose relative importance (preferences) is unknown to the agent. While this alleviates dependence on scalar reward design, the expected return of a policy can change significantly with varying preferences, making it challenging to learn a single model to produce optimal policies under different preference conditions. We propose a generalized version of the Bellman equation to learn a single parametric representation for optimal policies over the space of all possible preferences. After an initial learning phase, our agent can execute the optimal policy under any given preference, or automatically infer an underlying preference with very few samples. Experiments across four different domains demonstrate the effectiveness of our approach.

AB - We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks. In MORL, the aim is to learn policies over multiple competing objectives whose relative importance (preferences) is unknown to the agent. While this alleviates dependence on scalar reward design, the expected return of a policy can change significantly with varying preferences, making it challenging to learn a single model to produce optimal policies under different preference conditions. We propose a generalized version of the Bellman equation to learn a single parametric representation for optimal policies over the space of all possible preferences. After an initial learning phase, our agent can execute the optimal policy under any given preference, or automatically infer an underlying preference with very few samples. Experiments across four different domains demonstrate the effectiveness of our approach.

UR - https://www.scopus.com/pages/publications/85084150576

UR - https://www.scopus.com/pages/publications/85084150576#tab=citedBy

M3 - Conference article

SN - 1049-5258

VL - 32

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

T2 - 33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019

Y2 - 8 December 2019 through 14 December 2019

ER -