# LacaDM: A Latent Causal Diffusion Model for Multiobjective Reinforcement Learning

arXiv: https://arxiv.org/abs/2512.19516 · HTML: https://mlsanity.com/paper/2512.19516/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 22 Dec 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

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

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2305.18459/) (2023)
- [Learning Temporally Causal Latent Processes from General Temporal Data](https://mlsanity.com/paper/2110.05428/) (2021)
- [A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization](https://mlsanity.com/paper/2406.01661/) (2024)
- [Pareto Set Learning for Expensive Multi-Objective Optimization](https://mlsanity.com/paper/2210.08495/) (2022)
- [A Survey on Causal Reinforcement Learning](https://mlsanity.com/paper/2302.05209/) (2023)
- [Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL](https://mlsanity.com/paper/2305.00567/) (2023)
- [Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework](https://mlsanity.com/paper/2311.12495/) (2023)
- [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)
- [First Hitting Diffusion Models for Generating Manifold, Graph and Categorical Data](https://mlsanity.com/paper/2209.01170/) (2022)
- [Audio Generation with Multiple Conditional Diffusion Model](https://mlsanity.com/paper/2308.11940/) (2023)
- [Multi-objective Aerial Collaborative Secure Communication Optimization via Generative Diffusion Model-enabled Deep Reinforcement Learning](https://mlsanity.com/paper/2407.08914/) (2024)
- [Inverse Reinforcement Learning by Estimating Expertise of Demonstrators](https://mlsanity.com/paper/2402.01886/) (2024)
- [Expensive Multi-Objective Bayesian Optimization Based on Diffusion Models](https://mlsanity.com/paper/2405.08674/) (2024)
- [Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2405.16390/) (2024)
- [EmoDM: A Diffusion Model for Evolutionary Multi-objective Optimization](https://mlsanity.com/paper/2401.15931/) (2024)
- [A Generalized Scalarization Method for Evolutionary Multi-Objective Optimization](https://mlsanity.com/paper/2212.01545/) (2022)

## Built on by (most cited first, 1 of 1)

- [Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior](https://mlsanity.com/paper/2601.01966/) (2026)

## Abstract (arXiv)

Multiobjective reinforcement learning (MORL) poses significant challenges due to the inherent conflicts between objectives and the difficulty of adapting to dynamic environments. Traditional methods often struggle to generalize effectively, particularly in large and complex state-action spaces. To address these limitations, we introduce the Latent Causal Diffusion Model (LacaDM), a novel approach designed to enhance the adaptability of MORL in discrete and continuous environments. Unlike existing methods that primarily address conflicts between objectives, LacaDM learns latent temporal causal relationships between environmental states and policies, enabling efficient knowledge transfer across diverse MORL scenarios. By embedding these causal structures within a diffusion model-based framework, LacaDM achieves a balance between conflicting objectives while maintaining strong generalization capabilities in previously unseen environments. Empirical evaluations on various tasks from the MOGymnasium framework demonstrate that LacaDM consistently outperforms the state-of-art baselines in terms of hypervolume, sparsity, and expected utility maximization, showcasing its effectiveness in complex multiobjective tasks.