Learning Control Policies for Variable Objectives from Offline Data

Abstract

Offline reinforcement learning provides a viable approach to obtain advanced control strategies for dynamical systems, in particular when direct interaction with the environment is not available. In this paper, we introduce a conceptual extension for model-based policy search methods, called variable objective policy (VOP). With this approach, policies are trained to generalize efficiently over a variety of objectives, which parameterize the reward function. We demonstrate that by altering the objectives passed as input to the policy, users gain the freedom to adjust its behavior or re-balance optimization targets at runtime, without need for collecting additional observation batches or re-training.

arXiv comment8 pages, 7 figures

References in corpus (7)

• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction
• D4RL: Datasets for Deep Data-Driven Reinforcement Learning
• Behavior Regularized Offline Reinforcement Learning
• A Benchmark Environment Motivated by Industrial Control Problems
• RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning
• Batch Reinforcement Learning on the Industrial Benchmark: First Experiences