# Post Hoc Extraction of Pareto Fronts for Continuous Control

arXiv: https://arxiv.org/abs/2603.02628 · HTML: https://mlsanity.com/paper/2603.02628/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [A Practical Guide to Multi-Objective Reinforcement Learning and Planning](https://mlsanity.com/paper/2103.09568/) (2021)
- [A Survey of Multi-Objective Sequential Decision-Making](https://mlsanity.com/paper/1402.0590/) (2014)
- [A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation](https://mlsanity.com/paper/1908.08342/) (2019)
- [Dynamic Weights in Multi-Objective Deep Reinforcement Learning](https://mlsanity.com/paper/1809.07803/) (2018)
- [Evolution-Guided Policy Gradient in Reinforcement Learning](https://mlsanity.com/paper/1805.07917/) (2018)
- [PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm](https://mlsanity.com/paper/2208.07914/) (2022)
- [Smooth Tchebycheff Scalarization for Multi-Objective Optimization](https://mlsanity.com/paper/2402.19078/) (2024)
- [Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL](https://mlsanity.com/paper/2305.00567/) (2023)
- [Meta-Learning for Multi-objective Reinforcement Learning](https://mlsanity.com/paper/1811.03376/) (2018)
- [Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework](https://mlsanity.com/paper/2311.12495/) (2023)
- [Proximal Distilled Evolutionary Reinforcement Learning](https://mlsanity.com/paper/1906.09807/) (2019)
- [Pareto Conditioned Networks](https://mlsanity.com/paper/2204.05036/) (2022)
- [Pareto Set Learning for Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2501.06773/) (2025)
- [Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data Coverage](https://mlsanity.com/paper/2310.18434/) (2023)
- [Policy-regularized Offline Multi-objective Reinforcement Learning](https://mlsanity.com/paper/2401.02244/) (2024)

## Abstract (arXiv)

Agents in the real world must often balance multiple objectives, such as speed, stability, and energy efficiency in continuous control. To account for changing conditions and preferences, an agent must ideally learn a Pareto frontier of policies representing multiple optimal trade-offs. Recent advances in multi-policy multi-objective reinforcement learning (MORL) enable learning a Pareto front directly, but require full multi-objective consideration from the start of training. In practice, multi-objective preferences often arise after a policy has already been trained on a single specialised objective. Existing MORL methods cannot leverage these pre-trained `specialists' to learn Pareto fronts and avoid incurring the sample costs of retraining. We introduce Mixed Advantage Pareto Extraction (MAPEX), an offline MORL method that constructs a frontier of policies by reusing pre-trained specialist policies, critics, and replay buffers. MAPEX combines evaluations from specialist critics into a mixed advantage signal, and weights a behaviour cloning loss with it to train new policies that balance multiple objectives. MAPEX's post hoc Pareto front extraction preserves the simplicity of single-objective off-policy RL, and avoids retrofitting these algorithms into complex MORL frameworks. We formally describe the MAPEX procedure and evaluate MAPEX on five multi-objective MuJoCo environments. Given the same starting policies, MAPEX produces comparable fronts at 0.001% the sample cost of established baselines.