Related papers: Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems

Related papers

HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning [95.29291773706224]
Tool-Integrated Reasoning is a capability for LLM agents to solve complex tasks by interacting with external tools iteratively.<n>Existing approaches typically assign uniform trajectory-level advantages and treat all correct tool calls equally.<n>This can lead to imprecise learning signals that do not adequately distinguish between trivial and challenging tool-use patterns.
arXiv Detail & Related papers (2026-08-22T09:14:15Z)
Sample-Efficient Neurosymbolic Deep Reinforcement Learning [49.60927398960061]
We propose a neuro-symbolic Deep RL approach that integrates background symbolic knowledge to improve sample efficiency.<n>Online reasoning is performed to guide the training process through two mechanisms.<n>We show improved performance over a state-of-the-art reward machine baseline.
arXiv Detail & Related papers (2026-01-06T09:28:53Z)
Dynamic Rank Reinforcement Learning for Adaptive Low-Rank Multi-Head Self Attention in Large Language Models [0.0]
We propose Dynamic Rank Reinforcement Learning (DR-RL), a novel framework that adaptively optimize the low-rank factorization of Multi-Head Self-Attention (MHSA) in Large Language Models (LLMs)<n>DR-RL maintains downstream accuracy statistically equivalent to full-rank attention while significantly reducing Floating Point Operations (FLOPs)<n>This work bridges the gap between adaptive efficiency and theoretical rigor in MHSA, offering a principled, mathematically grounded alternative to rank reduction techniques in resource-constrained deep learning.
arXiv Detail & Related papers (2025-12-17T21:09:19Z)
Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution [76.66229730098759]
In real-world image super-resolution (Real-ISR), existing approaches mainly rely on fine-tuning pre-trained diffusion models.<n>We propose a Mixture-of-Ranks (MoR) architecture for single-step image super-resolution.<n>We introduce a fine-grained expert partitioning strategy that treats each rank in LoRA as an independent expert.
arXiv Detail & Related papers (2025-11-20T04:11:44Z)
Dynamic Reward Scaling for Multivariate Time Series Anomaly Detection: A VAE-Enhanced Reinforcement Learning Approach [1.332091725929965]
This paper presents a deep reinforcement learning framework that combines a Variational Autoencoder (VAE), an LSTM-based Deep Q-Network (DQN), dynamic reward shaping, and an active learning module to address these issues in a unified learning framework.
arXiv Detail & Related papers (2025-11-15T20:36:20Z)
Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation [60.04281435591454]
CRDA (Curriculum Reinforcement-Learning Data Augmentation) is a novel framework guiding detectors to progressively master multi-domain forgery features.<n>Central to our approach is integrating reinforcement learning and causal inference.<n>Our method significantly improves detector generalizability, outperforming SOTA methods across multiple cross-domain datasets.
arXiv Detail & Related papers (2025-11-10T12:45:52Z)
ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning [17.928214942495412]
ACPO employs a dynamic curriculum that orchestrates a principled transition from a stable, near on-policy exploration phase to an efficient, off-policy exploitation phase.<n>We conduct extensive experiments on a suite of challenging multimodal reasoning benchmarks, including MathVista, LogicVista, and MMMU-Pro.<n>Results demonstrate that ACPO consistently outperforms strong baselines such as DAPO and PAPO, achieving state-of-the-art performance, accelerated convergence, and superior training stability.
arXiv Detail & Related papers (2025-10-01T09:11:27Z)
Agentic Reinforced Policy Optimization [66.96989268893932]
Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
arXiv Detail & Related papers (2025-07-26T07:53:11Z)
QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning? [4.429189958406034]
Credit assignment has remained a fundamental challenge in multi-agent reinforcement learning (MARL)<n>We propose a novel algorithm, textbfQLLM, which facilitates the automatic construction of credit assignment functions using large language models (LLMs)<n>Extensive experiments conducted on several standard MARL benchmarks demonstrate that the proposed method consistently outperforms existing state-of-the-art baselines.
arXiv Detail & Related papers (2025-04-17T14:07:11Z)
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [70.91804882618243]
This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.<n>We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge.<n>Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
arXiv Detail & Related papers (2025-02-18T02:37:26Z)
Towards Foundational Models for Dynamical System Reconstruction: Hierarchical Meta-Learning via Mixture of Experts [0.7373617024876724]
We introduce MixER: Mixture of Expert Reconstructors, a novel sparse top-1 MoE layer employing a custom gating update algorithm based on $K$-means and least squares.<n>Experiments validate MixER's capabilities, demonstrating efficient training and scalability to systems of up to ten ordinary parametric differential equations.<n>Our layer underperforms state-of-the-art meta-learners in high-data regimes, particularly when each expert is constrained to process only a fraction of a dataset composed of highly related data points.
arXiv Detail & Related papers (2025-02-07T21:16:43Z)
Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting [26.141054975797868]
We propose a novel Adaptive Multi-Scale Decomposition (AMD) framework for time series forecasting (TSF) Our framework decomposes time series into distinct temporal patterns at multiple scales, leveraging the Multi-Scale Decomposable Mixing (MDM) block. Our approach effectively models both temporal and channel dependencies and utilizes autocorrelation to refine multi-scale data integration.
arXiv Detail & Related papers (2024-06-06T05:27:33Z)
MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wild [81.32127423981426]
Multimodal emotion recognition based on audio and video data is important for real-world applications. Recent methods have focused on exploiting advances of self-supervised learning (SSL) for pre-training of strong multimodal encoders. We propose a different perspective on the problem and investigate the advancement of multimodal DFER performance by adapting SSL-pre-trained disjoint unimodal encoders.
arXiv Detail & Related papers (2024-04-13T13:39:26Z)
Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
arXiv Detail & Related papers (2024-02-09T07:45:26Z)
Self-Sustaining Multiple Access with Continual Deep Reinforcement Learning for Dynamic Metaverse Applications [17.436875530809946]
The Metaverse is a new paradigm that aims to create a virtual environment consisting of numerous worlds, each of which will offer a different set of services. To deal with such a dynamic and complex scenario, one potential approach is to adopt self-sustaining strategies. This paper investigates the problem of multiple access in multi-channel environments to maximize the throughput of the intelligent agent.
arXiv Detail & Related papers (2023-09-18T22:02:47Z)
REX: Rapid Exploration and eXploitation for AI Agents [103.68453326880456]
We propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX. REX introduces an additional layer of rewards and integrates concepts similar to Upper Confidence Bound (UCB) scores, leading to more robust and efficient AI agent performance.
arXiv Detail & Related papers (2023-07-18T04:26:33Z)
PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement Learning [25.84621883831624]
Hierarchical reinforcement learning (HRL) has the potential to solve complex long horizon tasks using temporal abstraction and increased exploration.<n>We present primitive enabled adaptive relabeling (PEAR)<n>We first perform adaptive relabeling on a few expert demonstrations to generate efficient subgoal supervision.<n>We then jointly optimize HRL agents by employing reinforcement learning (RL) and imitation learning (IL)
arXiv Detail & Related papers (2023-06-10T09:41:30Z)
Unifying Synergies between Self-supervised Learning and Dynamic Computation [53.66628188936682]
We present a novel perspective on the interplay between SSL and DC paradigms. We show that it is feasible to simultaneously learn a dense and gated sub-network from scratch in a SSL setting. The co-evolution during pre-training of both dense and gated encoder offers a good accuracy-efficiency trade-off.
arXiv Detail & Related papers (2023-01-22T17:12:58Z)
Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
arXiv Detail & Related papers (2021-07-08T18:01:02Z)
The reinforcement learning-based multi-agent cooperative approach for the adaptive speed regulation on a metallurgical pickling line [0.0]
The proposed approach combines mathematical modeling as a base algorithm and a cooperative Multi-Agent Reinforcement Learning system. We demonstrate how Deep Q-Learning can be applied to a real-life task in a heavy industry, resulting in significant improvement of previously existing automation systems.
arXiv Detail & Related papers (2020-08-16T15:10:39Z)
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning [102.78958681141577]
We present SUNRISE, a simple unified ensemble method, which is compatible with various off-policy deep reinforcement learning algorithms. SUNRISE integrates two key ingredients: (a) ensemble-based weighted Bellman backups, which re-weight target Q-values based on uncertainty estimates from a Q-ensemble, and (b) an inference method that selects actions using the highest upper-confidence bounds for efficient exploration.
arXiv Detail & Related papers (2020-07-09T17:08:44Z)

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