Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

226451677902 · Jun 202019922001200920172026
48 results for Decentralized Policy Optimization

New MARL algorithms resolve the curse of multiagency with function approximation.

problem Challenges in Multi-Agent Reinforcement Learning (MARL) due to the curse of multiagency.
method V-Learning with Policy Replay and Decentralized Optimistic Policy Mirror Descent.
result First polynomial sample complexity results for learning approximate Coarse Correlated Equilibria (CCEs) of Markov Games under decentralized linear function approximation.

Flexible decentralized MARL framework for cooperative multi-agent learning.

problem Complexity and impracticality of centralized MARL in complicated applications.
method Flexible fully-decentralized actor-critic MARL framework using primal-dual hybrid gradient descent.
result Competitive performance in large-scale cooperative multi-agent environments.

DePAint solves MARL for agents with local constraints, privacy, and no central controller.

problem Training multi-agent systems to optimize rewards while adhering to safety constraints in a decentralized setting.
method Formulated as a decentralized constrained multi-agent Markov Decision Problem, proposed DePAint method using momentum-based decentralized policy gradient.
result First privacy-preserving fully decentralized MARL algorithm considering both peak and average constraints.

A decentralized policy achieves logarithmic regret for multi-agent MAB problems with communication constraints.

problem Decentralized policy for multi-agent MAB problems with option availability and communication constraints.
method Upper Confidence Bound (UCB) algorithms with non-stationary stochastic communication protocol.
result Guaranteed logarithmic regret for non-fully connected spatial graphs with communication constraints.

Improves data efficiency in multi-agent control tasks using model-based reinforcement learning.

problem Limited data efficiency in reinforcement learning for multi-agent tasks.
method Decentralized model-based policy optimization (DMPO) framework.
result DMPO achieves superior data efficiency and matches model-free methods using true models.

Policy-gradient method controls multiple non-cohesive targets.

problem Controlling multiple non-cohesive targets in a decentralized manner.
method Proximal Policy Optimization for target selection and driving.
result Effective control of non-cohesive targets without prior dynamics knowledge.

Expectation maximization (EM) has recently been shown to be an efficient algorithm for learning finite-state controllers (FSCs) in large decentralized POMDPs (Dec-POMDPs). However, current methods use fixed-size FSCs and often converge to maxima that are far from optimal. This paper considers a variable-size FSC to rep…

2015-05-01abs ↗pdf ↗

Improved exploration in cooperative multi-agent reinforcement learning.

problem Limited expressiveness of Gaussian policies in DecSPG hinders effective exploration.
method Proposes decentralized diffusion policy learning (DDPL) with denoising diffusion probabilistic models.
result Consistently improved performance on various MARL benchmarks.

This paper proposes a decentralized reinforcement learning method for multi-agent resource allocation.

problem Allocating heterogeneous resources among multiple agents in a decentralized manner.
method Liquid-Graph-Time Clustering-IPPO, integrating dynamic cluster consensus.
result LGTC-IPPO achieves more stable rewards, better coordination, and robust performance.

Algorithm converges to Nash equilibria in competitive games.

problem Finding Nash equilibria in decentralized, competitive Markov games.
method Decentralized Optimistic Gradient Descent/Ascent with a critic.
result Converges to the set of Nash equilibria under self-play.

DORIS algorithm achieves no-regret learning in Markov games with adversarial opponents.

problem Decentralized policy learning in Markov games with nonstationary opponents.
method DORIS algorithm using optimistic hyperpolicy mirror descent.
result Achieves K\sqrt{K}-regret in general function approximation.

A decentralized routing framework for lunar exploration robots.

problem Routing data in intermittent connectivity lunar networks.
method Graph Attention-based Multi-Agent Reinforcement Learning (GAT-MARL).
result Higher delivery rates, no duplications, fewer packet losses.

We propose a method to model multi-agent behaviors with limited observation and mechanical constraints.

problem Modeling real-world multi-agent behaviors with limited observation and mechanical constraints.
method Decentralized generative models with partial observation and mechanical constraints based on hierarchical variational recurrent neural networks.
result Our method effectively models and predicts biologically plausible behaviors with minimal constraint violations.

D-SPIDER-SFO solves nonconvex optimization problems faster on decentralized networks.

problem Finding a decentralized algorithm with similar convergence rate to SPIDER-SFO.
method Proposed D-SPIDER-SFO, a decentralized variant of SPIDER-SFO.
result Achieves a similar gradient computation cost to centralized SPIDER-SFO.

New framework for decentralized optimization of upper-linearizable functions with improved regret and complexity.

problem Decentralized optimization of upper-linearizable functions with general constraints.
method Decentralized projection-free optimization with upper-linearizable function framework.
result Regret of O(T1θ/2)O(T^{1-θ/2}) with communication complexity of O(Tθ)O(T^θ) and linear optimization calls of O(T2θ)O(T^{2θ}).

Fairness is essential for human society, contributing to stability and productivity. Similarly, fairness is also the key for many multi-agent systems. Taking fairness into multi-agent learning could help multi-agent systems become both efficient and stable. However, learning efficiency and fairness simultaneously is a …

2019-10-31abs ↗pdf ↗

Proposes three decentralized multi-agent reinforcement learning algorithms to reduce network congestion.

problem Finding a joint policy maximizing long-term return in a decentralized multi-agent system.
method Three fully decentralized multi-agent natural actor-critic (MAN) algorithms using linear function approximations.
result The proposed algorithms achieve performance comparable to or better than standard methods in reducing network congestion.

Unified framework for decentralized bilevel optimization with various heterogeneity-correction strategies.

problem Decentralized bilevel optimization with neighborhood communications and data heterogeneity.
method SPARKLE: Single-loop Primal-dual Algorithm for decentralized bilevel optimization, incorporating various heterogeneity-correction techniques.
result Unified convergence analysis for SPARKLE with state-of-the-art convergence rates compared to existing algorithms.

Bayesian network approach for efficient cooperative MARL.

problem Leveraging inter-agent coupling information for scalable MARL algorithms.
method Modeling cooperative MARL via Bayesian networks, identifying value dependency sets, proposing P-DTDE paradigm.
result P-DTDE policy gradient estimator has lower total variance than CTDE.

A novel decentralized algorithm improves minimax optimization in federated learning.

problem Minimax optimization in federated learning with data heterogeneity.
method Decentralized Gradient Tracking (K-GT-Minimax) for nonconvex-strongly-concave optimization.
result Demonstrates superior convergence rate for NC-SC minimax optimization.

Enhances parallelism in decentralized learning for larger networks.

problem Scalability limitations in decentralized learning with increasing number of machines.
method Proposes Decentralized Anytime SGD, a novel algorithm that extends parallelism threshold.
result Establishes a theoretical upper bound on parallelism surpassing current state-of-the-art.

Optimal contracts help principals delegate data collection in decentralized ML.

problem Dealing with information asymmetries in decentralized ML.
method Design of optimal and near-optimal contracts addressing uncertainty in model quality and performance.
result Simple linear contracts achieve 1-1/e fraction of optimal utility.

Two new algorithms optimize decentralized convex optimization with reduced communication rounds.

problem Decentralized minimization of smooth strongly convex functions in a network.
method Proposes two new algorithms based on accelerated Forward Backward methods.
result First algorithm is optimal in terms of communication rounds and gradient computations.

This paper examines market misconduct in DeFi and proposes regulatory solutions.

problem Novel forms of market misconduct in DeFi.
method Comprehensive analysis, comparative study, empirical measurements, and tailored regulatory framework investigation.
result Identification of key areas for regulatory enhancement in DeFi.

The paper analyzes stability and generalization of decentralized SGD.

problem Stability and generalization of decentralized stochastic gradient descent.
method Novel formulation of decentralized stochastic gradient descent combined with non/convex optimization theory.
result First stability and generalization guarantees for decentralized stochastic gradient descent.

VRSGT algorithm reduces orthogonality constraints in decentralized optimization.

problem Decentralized optimization with orthogonality constraints.
method VRSGT algorithm with variance reduction and orthogonal techniques.
result VRSGT achieves convergence rate of O(1 / k) for orthogonality constraints.

AdaSDBO solves decentralized bilevel optimization without problem parameters, achieving competitive performance.

problem Decentralized bilevel optimization problems without known parameters.
method AdaSDBO, a fully problem-parameter-free algorithm with adaptive stepsizes.
result AdaSDBO achieves a convergence rate of $\widetilde{\mathcal{O}}\left(\frac{1}{T} ight)$, matching state-of-the-art methods up to polylogarithmic factors.

A new algorithm reduces communication in decentralized optimization.

problem Reducing communication in decentralized optimization problems.
method Adaptive randomized communication-efficient algorithmic framework that periodically tracks disagreement error and selects influential edges for communication.
result Strong theoretical convergence guarantees and performance quantification under standard assumptions.

Hybrid Policy Optimization tackles reinforcement learning in hybrid spaces, improving performance over PPO.

problem Credit assignment issues and biased gradients in hybrid discrete-continuous action spaces.
method Mixed gradient estimator combining pathwise and score-function gradients, reformulating problems in hybrid form.
result HPO substantially outperforms PPO on inventory control and switched systems, with performance gaps increasing with continuous action dimension.

Research proposes a decentralized invoice discounting system using Kelly criterion.

problem Persistent funding gap for SMEs and inefficiencies in traditional factoring.
method Automated Market Maker (AMM) with Kelly criterion for premium calculation.
result Resilient decentralized system with optimal profit distribution policies.

New algorithm reduces complexity in multi-agent reinforcement learning.

problem High computational complexity in exact computations for multi-agent reinforcement learning.
method Design of a scalable algorithm based on Natural Policy Gradient, using local information and limited communication.
result Converges to globally optimal policy with dimension-free complexity and localization error.

DESTRESS optimizes decentralized nonconvex optimization with optimal IFO complexity and efficient communication.

problem Decentralized nonconvex finite-sum optimization in multi-agent systems.
method DESTRESS uses stochastic recursive gradient updates, gradient tracking, and careful hyper-parameter choices to achieve optimal IFO complexity with efficient communication.
result DESTRESS matches the optimal IFO complexity of centralized algorithms while maintaining communication efficiency.