On Preference Coverage Collapse from Hindsight Relabeling in Multi-Objective Reinforcement Learning

arXiv:2609.26918 · cs.LG, cs.AI · Submitted 2026-09-22 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-22

Updated: 2026-09-22

Terminology

• Reinforcement Learning — 21× in this paper · explained in 4 episodes
• Preference Coverage Collapse — 7× in this paper
• Actor — 6× in this paper · explained in 3 episodes
• Abandoned Preference Mass — 5× in this paper
• Deep Reinforcement Learning — 5× in this paper · explained in 2 episodes
• Hindsight Experience Replay — 4× in this paper
• Ablation — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 4 episodes
• Core — 2× in this paper · explained in 2 episodes
• Generalized Policy Improvement — 2× in this paper
• Prioritized Experience Replay — 2× in this paper
• Q-learning — 2× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Reward Function — 2× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Concave-Augmented Pareto Q-Learning — 1× in this paper
• Expected Utility Metric — 1× in this paper
• Generalization — 1× in this paper · explained in 13 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes

Sources

• Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization
• Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
• PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm
• Diversity is All You Need: Learning Skills without a Reward Function
• A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets
• Continuous control with deep reinforcement learning
• Multi-Objective Deep Reinforcement Learning
• Prioritized Experience Replay
• Hindsight Preference Replay Improves Preference-Conditioned Multi-Objective Reinforcement Learning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks