Multi-Objective Deep Reinforcement Learning
This addresses multi-objective decision problems in AI/robotics where trade-offs between objectives are unclear, though it appears incremental as it builds on existing reinforcement learning techniques.
The authors tackled the problem of high-dimensional multi-objective decision-making with unknown objective importances by proposing Deep Optimistic Linear Support Learning (DOL), which computes a convex coverage set of optimal solutions and is claimed as the first successful deep reinforcement learning method for multi-objective policies.
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.