Moment Matching Q-Learning

• URL: http://arxiv.org/abs/2605.29033v1
• Date: Wed, 27 May 2026 19:33:51 GMT
• Title: Moment Matching Q-Learning
• Abstract summary: We propose a new framework named Moment Matching Q-Learning (MoMa QL)<n>MoMa QL utilizes a technique from statistical hypothesis testing known as maximum mean discrepancy (MMD) that intend to match all orders of statistics between the original and target distribution.<n>We show that our method MoMa QL is more computationally efficient with a comparable if not competitive performance in various D4RL tasks.
• Score: 42.00659383997804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Score-based and flow-based generative models exhibit remarkable expressive capacity in capturing complex distributions, and have been extensively deployed in tasks ranging from image generation to reinforcement learning. Nevertheless, these models suffer from prolonged inference latency, which imposes a significant computational bottleneck in RL with iterative sampling. To overcome this limitation, we propose a new framework named Moment Matching Q-Learning (MoMa QL), which utilizes a technique from statistical hypothesis testing known as maximum mean discrepancy (MMD) that intend to match all orders of statistics between the original and target distribution. By enforcing strong regularization on all moment statistics, this algorithm guarantees distribution-level convergence for conditional score function and remains stable under various hyperparameters. Empirically, we show that our method MoMa QL is more computationally efficient with a comparable if not competitive performance in various D4RL tasks. Remarkably, by accelerating the action sampling process for flow-based policies, MoMa QL demonstrates superior performance in offline-to-online RL tasks because of faster and stronger adaptability for online interactive finetuning.

Related papers

• Efficient Analytic Uncertainty Quantification for Multi-Modal Regression [26.64106355159076]
  We introduce a unified, distribution-agnostic framework that simultaneously achieves accurate estimation of complex conditional distributions.<n>Our framework outperforms state-of-the-art multi-modal regression baselines, and even matches predictive performance of computationally expensive ensemble models.
  arXiv  Detail & Related papers  (2026-06-23T21:31:42Z)
• Reversal Q-Learning [57.43956630070019]
  Reversal Q-learning is an off-policy RL algorithm that trains a flow policy based on prior data.<n>We show that RQL leads to the best average offline RL performance compared to state-of-the-art flow-based offline RL algorithms.
  arXiv  Detail & Related papers  (2026-06-16T05:56:10Z)
• Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes [46.91576262410701]
  We present a novel model-based algorithm for discrete NMRDPs that factorizes Markovian transition learning from non-Markovian reward handling via reward machines.<n>We experimentally compare our method with modern state-of-the-art model-based RL approaches on environments of increasing complexity.
  arXiv  Detail & Related papers  (2025-12-16T17:26:24Z)
• QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution [53.13952833016505]
  We propose a low-bit quantization model for real-world video super-resolution (VSR)<n>We use a calibration dataset to measure both spatial and temporal complexity for each layer.<n>We refine the FP and low-bit branches to achieve simultaneous optimization.
  arXiv  Detail & Related papers  (2025-08-06T14:35:59Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)
• On Practical Robust Reinforcement Learning: Practical Uncertainty Set and Double-Agent Algorithm [11.748284119769039]
  Robust reinforcement learning (RRL) aims at seeking a robust policy to optimize the worst case performance over an uncertainty set of Markov decision processes (MDPs)
  arXiv  Detail & Related papers  (2023-05-11T08:52:09Z)
• Single-partition adaptive Q-learning [0.0]
  Single- Partition adaptive Q-learning (SPAQL) is an algorithm for model-free episodic reinforcement learning. Tests on episodes with a large number of time steps show that SPAQL has no problems scaling, unlike adaptive Q-learning (AQL) We claim that SPAQL may have a higher sample efficiency than AQL, thus being a relevant contribution to the field of efficient model-free RL methods.
  arXiv  Detail & Related papers  (2020-07-14T00:03:25Z)
• Simultaneously Evolving Deep Reinforcement Learning Models using Multifactorial Optimization [18.703421169342796]
  This work proposes a framework capable of simultaneously evolving several DQL models towards solving interrelated Reinforcement Learning tasks. A thorough experimentation is presented and discussed so as to assess the performance of the framework.
  arXiv  Detail & Related papers  (2020-02-25T10:36:57Z)

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.