# MOCHA: Multi-Objective Co-Design using Hypernetwork Architectures

arXiv: https://arxiv.org/abs/2609.30570 · HTML: https://mlsanity.com/paper/2609.30570/

## 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 27 of its 43 references that are in the map.
- First posted on arXiv 24 Sep 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, 27 of 27)

- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [Scalable Global Optimization via Local Bayesian Optimization](https://mlsanity.com/paper/1910.01739/) (2019)
- [pymoo: Multi-objective Optimization in Python](https://mlsanity.com/paper/2002.04504/) (2020)
- [Embodied Intelligence via Learning and Evolution](https://mlsanity.com/paper/2102.02202/) (2021)
- [Preparing for the Unknown: Learning a Universal Policy with Online System Identification](https://mlsanity.com/paper/1702.02453/) (2017)
- [PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm](https://mlsanity.com/paper/2208.07914/) (2022)
- [GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots](https://mlsanity.com/paper/2209.05309/) (2022)
- [Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots](https://mlsanity.com/paper/2201.09863/) (2022)
- [Hardware Conditioned Policies for Multi-Robot Transfer Learning](https://mlsanity.com/paper/1811.09864/) (2018)
- [One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion](https://mlsanity.com/paper/2409.06366/) (2024)
- [Hypernetworks in Meta-Reinforcement Learning](https://mlsanity.com/paper/2210.11348/) (2022)
- [Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design](https://mlsanity.com/paper/2110.03659/) (2021)
- [Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning](https://mlsanity.com/paper/1911.06832/) (2019)
- [Multi-Objective Graph Heuristic Search for Terrestrial Robot Design](https://mlsanity.com/paper/2107.05858/) (2021)
- [Pareto Set Learning for Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2501.06773/) (2025)
- [Hypernetworks for Zero-shot Transfer in Reinforcement Learning](https://mlsanity.com/paper/2211.15457/) (2022)
- [Recurrent Hypernetworks are Surprisingly Strong in Meta-RL](https://mlsanity.com/paper/2309.14970/) (2023)
- [AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2505.23708/) (2025)
- [N-LIMB: Neural Limb Optimization for Efficient Morphological Design](https://mlsanity.com/paper/2207.11773/) (2022)
- [Learning Pareto Set for Multi-Objective Continuous Robot Control](https://mlsanity.com/paper/2406.18924/) (2024)
- [Humanoid Robot Co-Design: Coupling Hardware Design with Gait Generation via Hybrid Zero Dynamics](https://mlsanity.com/paper/2308.10962/) (2023)
- [Toward Humanoid Brain-Body Co-design: Joint Optimization of Control and Morphology for Fall Recovery](https://mlsanity.com/paper/2510.22336/) (2025)
- [MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics](https://mlsanity.com/paper/2603.09237/) (2026)
- [Shape Your Body: Value Gradients for Multi-Embodiment Robot Design](https://mlsanity.com/paper/2606.00702/) (2026)

## Abstract (arXiv)

In this work, we present MOCHA, the first, to our knowledge, reinforcement learning based approach to computing a family of Pareto-optimal policies across the design space of a robot using a single network. Specifically, MOCHA leverages the hypernetwork architecture to learn a network that produces specialized network parameters optimized for a given objective and parameterized robot design; we term this a multi-objective design hypernetwork (MDH). We demonstrate the capabilities of MDHs to represent a complex family of design-dependent strategies on two distinct robot morphologies, each with six design dimensions and across 2-3 objectives. Moreover, we propose an approach for efficiently producing a Design Pareto set using evolutionary search of the learned policy network, generating the optimal design-policy combination for each objective prioritization. Lastly, we provide an efficient method for computing generalist robot designs which achieve the best cumulative performance across the entire set of objectives.