Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization

• URL: http://arxiv.org/abs/2511.01374v1
• Date: Mon, 03 Nov 2025 09:17:53 GMT
• Title: Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization
• Authors: Ziqi Wang, Jiashun Liu, Ling Pan,
• Abstract summary: In this paper, we reformulate existing intractable multimodal actors within a unified framework.<n>We then propose a distance-based diversity regularization that does not explicitly require decision probabilities.<n>Our experiments highlight that the amortized actor is a promising policy model class with strong multimodal expressivity and high performance.
• Score: 24.229494482432376
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional continuous deep reinforcement learning (RL) algorithms employ deterministic or unimodal Gaussian actors, which cannot express complex multimodal decision distributions. This limitation can hinder their performance in diversity-critical scenarios. There have been some attempts to design online multimodal RL algorithms based on diffusion or amortized actors. However, these actors are intractable, making existing methods struggle with balancing performance, decision diversity, and efficiency simultaneously. To overcome this challenge, we first reformulate existing intractable multimodal actors within a unified framework, and prove that they can be directly optimized by policy gradient via reparameterization. Then, we propose a distance-based diversity regularization that does not explicitly require decision probabilities. We identify two diversity-critical domains, namely multi-goal achieving and generative RL, to demonstrate the advantages of multimodal policies and our method, particularly in terms of few-shot robustness. In conventional MuJoCo benchmarks, our algorithm also shows competitive performance. Moreover, our experiments highlight that the amortized actor is a promising policy model class with strong multimodal expressivity and high performance. Our code is available at https://github.com/PneuC/DrAC

Related papers

• Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models [67.45032003041399]
  We propose a novel Multi-Paradigm Collaborative Attack (MPCAttack) framework to boost the transferability of adversarial examples against MLLMs.<n>MPCO adaptively balances the importance of different paradigm representations and guides the global optimisation.<n>Our solution consistently outperforms state-of-the-art methods in both targeted and untargeted attacks on open-source and closed-source MLLMs.
  arXiv  Detail & Related papers  (2026-03-05T06:01:26Z)
• From Sparse Decisions to Dense Reasoning: A Multi-attribute Trajectory Paradigm for Multimodal Moderation [59.27094165576015]
  We propose a novel learning paradigm (UniMod) that transitions from sparse decision-making to dense reasoning traces.<n>By constructing structured trajectories encompassing evidence grounding, modality assessment, risk mapping, policy decision, and response generation, we reformulate monolithic decision tasks into a multi-dimensional boundary learning process.<n>We introduce specialized optimization strategies to decouple task-specific parameters and rebalance training dynamics, effectively resolving interference between diverse objectives in multi-task learning.
  arXiv  Detail & Related papers  (2026-01-28T09:29:40Z)
• Actor-Critic without Actor [4.94481688445056]
  We introduce Actor-Critic without Actor (ACA), a lightweight framework that eliminates the explicit actor network and instead generates actions directly from the field of a noise-level critic.<n>ACA achieves more favorable learning curves and competitive performance compared to both standard actor-critic and state-of-the-art diffusion-based methods.
  arXiv  Detail & Related papers  (2025-09-25T11:33:09Z)
• Principled Multimodal Representation Learning [99.53621521696051]
  Multimodal representation learning seeks to create a unified representation space by integrating diverse data modalities.<n>Recent advances have investigated the simultaneous alignment of multiple modalities, yet several challenges remain.<n>We propose Principled Multimodal Representation Learning (PMRL), a novel framework that achieves simultaneous alignment of multiple modalities.
  arXiv  Detail & Related papers  (2025-07-23T09:12:25Z)
• Decision Flow Policy Optimization [53.825268058199825]
  We show that generative models can effectively model complex multi-modal action distributions and achieve superior robotic control in continuous action spaces.<n>Previous methods usually adopt the generative models as behavior models to fit state-conditioned action distributions from datasets.<n>We propose Decision Flow, a unified framework that integrates multi-modal action distribution modeling and policy optimization.
  arXiv  Detail & Related papers  (2025-05-26T03:42:20Z)
• Offline Multi-agent Reinforcement Learning via Score Decomposition [51.23590397383217]
  offline cooperative multi-agent reinforcement learning (MARL) faces unique challenges due to distributional shifts.<n>This work is the first work to explicitly address the distributional gap between offline and online MARL.
  arXiv  Detail & Related papers  (2025-05-09T11:42:31Z)
• Continual Multimodal Contrastive Learning [99.53621521696051]
  Multimodal Contrastive Learning (MCL) advances in aligning different modalities and generating multimodal representations in a joint space.<n>However, a critical yet often overlooked challenge remains: multimodal data is rarely collected in a single process, and training from scratch is computationally expensive.<n>In this paper, we formulate CMCL through two specialized principles of stability and plasticity.<n>We theoretically derive a novel optimization-based method, which projects updated gradients from dual sides onto subspaces where any gradient is prevented from interfering with the previously learned knowledge.
  arXiv  Detail & Related papers  (2025-03-19T07:57:08Z)
• Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient [26.675822002049372]
  Deep Diffusion Policy Gradient (DDiffPG) is a novel actor-critic algorithm that learns from scratch multimodal policies. DDiffPG forms a multimodal training batch and utilizes mode-specific Q-learning to mitigate the inherent greediness of the RL objective. Our approach further allows the policy to be conditioned on mode-specific embeddings to explicitly control the learned modes.
  arXiv  Detail & Related papers  (2024-06-02T09:32:28Z)
• Multi-modal Latent Diffusion [8.316365279740188]
  Multi-modal Variational Autoencoders are a popular family of models that aim to learn a joint representation of the different modalities. Existing approaches suffer from a coherence-quality tradeoff, where models with good generation quality lack generative coherence across modalities. We propose a novel method that uses a set of independently trained, uni-modal, deterministic autoencoders.
  arXiv  Detail & Related papers  (2023-06-07T14:16:44Z)
• Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning [70.20191211010847]
  Offline reinforcement learning (RL) aims to learn an optimal policy using a previously collected static dataset. We introduce Diffusion Q-learning (Diffusion-QL) that utilizes a conditional diffusion model to represent the policy. We show that our method can achieve state-of-the-art performance on the majority of the D4RL benchmark tasks.
  arXiv  Detail & Related papers  (2022-08-12T09:54:11Z)
• Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning [7.020079427649125]
  We show that grasping distinguishable skills for some tasks with non-unique optima can be essential for further improving its learning efficiency and performance. We propose a probabilistic mixture-of-experts (PMOE) for multimodal policy, together with a novel gradient estimator for the indifferentiability problem.
  arXiv  Detail & Related papers  (2021-04-19T08:21:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.