Objective-Behavior Alignment: Diagnostics for MORL Policy Selection
For decision-makers using MORL, this work provides tools to inspect behavioral differences that objective values alone obscure, improving policy selection transparency.
The paper addresses the problem that policies with similar value vectors in multi-objective reinforcement learning can exhibit substantially different behaviors, which is hidden from decision-makers. It proposes a diagnostic workflow that automatically highlights behavioral variation along the Pareto front, validated on grid and continuous control benchmarks.
Real-world decision-making often requires optimizing multiple competing objectives simultaneously. In reinforcement learning (RL), this is typically addressed by combining reward signals into a single scalar objective via a scalarization function, which can be fragile: small changes in the weights can induce drastically different policies. Multi-objective reinforcement learning (MORL) instead produces sets of policies that explicitly represent trade-offs between objectives. However, these policies are typically presented to the decision maker only through their value vectors, which can obscure substantial behavioral variation: policies that induce distinct trajectories may appear indistinguishable when evaluated solely by expected returns. We propose an exploratory diagnostic workflow that automatically highlights behavioral variation along the Pareto front that objective values alone do not reveal, providing both quantitative and visual tools to support policy inspection. We validate our approach on simple grid examples and scale it to continuous control benchmarks, demonstrating that it remains effective as problem complexity increases.