# TREX: Trajectory Explanations for Multi-Objective Reinforcement Learning

arXiv: https://arxiv.org/abs/2603.21988 · HTML: https://mlsanity.com/paper/2603.21988/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods.
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Placed in

- Deep reinforcement learning methods / [RL for games and combinatorial optimization](https://mlsanity.com/deeprl/rl-for-games-and-combinatorial-optimization/)

## Builds on (most cited first, 13 of 13)

- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [Agent57: Outperforming the Atari Human Benchmark](https://mlsanity.com/paper/2003.13350/) (2020)
- [A Practical Guide to Multi-Objective Reinforcement Learning and Planning](https://mlsanity.com/paper/2103.09568/) (2021)
- [A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation](https://mlsanity.com/paper/1908.08342/) (2019)
- [Explainable Reinforcement Learning: A Survey](https://mlsanity.com/paper/2005.06247/) (2020)
- [Dynamic Weights in Multi-Objective Deep Reinforcement Learning](https://mlsanity.com/paper/1809.07803/) (2018)
- [Generation of Policy-Level Explanations for Reinforcement Learning](https://mlsanity.com/paper/1905.12044/) (2019)
- [Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL](https://mlsanity.com/paper/2305.00567/) (2023)
- [Explainable Deep Reinforcement Learning: State of the Art and Challenges](https://mlsanity.com/paper/2301.09937/) (2023)
- [Urban Driving with Multi-Objective Deep Reinforcement Learning](https://mlsanity.com/paper/1811.08586/) (2018)
- [Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning](https://mlsanity.com/paper/2204.05027/) (2022)
- [Explaining RL Decisions with Trajectories](https://mlsanity.com/paper/2305.04073/) (2023)
- [Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World](https://mlsanity.com/paper/2308.07741/) (2023)

## Abstract (arXiv)

Reinforcement Learning (RL) has demonstrated its ability to solve complex decision-making problems in a variety of domains, by optimizing reward signals obtained through interaction with an environment. However, many real-world scenarios involve multiple, potentially conflicting objectives that cannot be easily represented by a single scalar reward. Multi-Objective Reinforcement Learning (MORL) addresses this limitation by enabling agents to optimize several objectives simultaneously, explicitly reasoning about trade-offs between them. However, the ``black box" nature of the RL models makes the decision process behind chosen objective trade-offs unclear. Current Explainable Reinforcement Learning (XRL) methods are typically designed for single scalar rewards and do not account for explanations with respect to distinct objectives or user preferences. To address this gap, in this paper we propose TREX, a Trajectory based Explainability framework to explain Multi-objective Reinforcement Learning policies, based on trajectory attribution. TREX generates trajectories directly from the learned expert policy, across different user preferences and clusters them into semantically meaningful temporal segments. We quantify the influence of these behavioural segments on the Pareto trade-off by training complementary policies that exclude specific clusters, measuring the resulting relative deviation on the observed rewards and actions compared to the original expert policy. Experiments on multi-objective MuJoCo environments - HalfCheetah, Ant and Swimmer, demonstrate the framework's ability to isolate and quantify the specific behavioural patterns.