Navigating Trade-offs: Policy Summarization for Multi-Objective Reinforcement Learning
This work addresses the challenge for decision-makers in MORL by improving explainability through policy summarization, though it is incremental as it builds on existing clustering methods.
The paper tackles the problem of large, multi-dimensional solution sets in multi-objective reinforcement learning (MORL) by proposing a clustering approach that groups policies based on behavior and objective values, outperforming traditional k-medoids in four environments.
Multi-objective reinforcement learning (MORL) is used to solve problems involving multiple objectives. An MORL agent must make decisions based on the diverse signals provided by distinct reward functions. Training an MORL agent yields a set of solutions (policies), each presenting distinct trade-offs among the objectives (expected returns). MORL enhances explainability by enabling fine-grained comparisons of policies in the solution set based on their trade-offs as opposed to having a single policy. However, the solution set is typically large and multi-dimensional, where each policy (e.g., a neural network) is represented by its objective values. We propose an approach for clustering the solution set generated by MORL. By considering both policy behavior and objective values, our clustering method can reveal the relationship between policy behaviors and regions in the objective space. This approach can enable decision makers (DMs) to identify overarching trends and insights in the solution set rather than examining each policy individually. We tested our method in four multi-objective environments and found it outperformed traditional k-medoids clustering. Additionally, we include a case study that demonstrates its real-world application.