Multi-Objective Deep Reinforcement Learning

Abstract

We propose Deep Optimistic Linear Support Learning (DOL) to solve high-dimensional multi-objective decision problems where the relative importances of the objectives are not known a priori. Using features from the high-dimensional inputs, DOL computes the convex coverage set containing all potential optimal solutions of the convex combinations of the objectives. To our knowledge, this is the first time that deep reinforcement learning has succeeded in learning multi-objective policies. In addition, we provide a testbed with two experiments to be used as a benchmark for deep multi-objective reinforcement learning.

References in corpus (2)

• Massively Parallel Methods for Deep Reinforcement Learning
• Move Evaluation in Go Using Deep Convolutional Neural Networks

Cited by in corpus (6)

• Levels of explainable artificial intelligence for human-aligned conversational explanations
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning
• Value constrained model-free continuous control
• Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation
• Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning