Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

TREX: Trajectory Explanations for Multi-Objective Reinforcement Learning

Dilina Rajapakse, Juan C. Rosero, Ivana Dusparic

Abstract

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.

TREX: Trajectory Explanations for Multi-Objective Reinforcement Learning

Abstract

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.
Paper Structure (17 sections, 3 equations, 8 figures, 3 tables)

This paper contains 17 sections, 3 equations, 8 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Reinforcement Learning
  4. Multi-Objective Reinforcement Learning
  5. Explainable Reinforcement Learning
  6. Trajectory based Explainable Reinforcement Learning
  7. Explainable Multi-Objective Reinforcement Learning
  8. Methodology
  9. Preference-Level analysis (PLA)
  10. Attribution Analysis
  11. Experimental Setup
  12. Results
  13. Preference Level Analysis - Quantitative Results
  14. Preference Level Analysis - Qualitative Results
  15. Discussion
  16. ...and 2 more sections

Figures (8)

  • Figure 1: Overview of the Preference-Level Analysis (PLA) pipeline: (1) sampling trajectories from an expert agent, (2) encoding sub-trajectories into latent space embeddings, (3) clustering trajectories into semantically distinct behaviours, (4) training original policy alongside complementary policies that iteratively exclude specific cluster trajectories, and (5) conducting attribution analysis to quantify the behavioural influence of each cluster.
  • Figure 2: MuJoCo multi-objective environments
  • Figure 3: MO-HalfCheetah trajectories for the clusters with (0.5, 0.5) user-preference
  • Figure 4: MO-Ant trajectories for the clusters with (0.5, 0.5) user-preference
  • Figure 5: MO-Ant Cluster 2 trajectory with (0.25, 0.75) user-preference
  • ...and 3 more figures