This work analyzes batch MARL with networked agents, providing finite-sample bounds.
problem Understanding the theoretical foundation of decentralized batch MARL with networked agents.
method Developed batch MARL algorithms for two settings: collaborative and competitive networks, without a central controller.
result Quantified finite-sample errors of estimated action-value functions for both settings.
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.
Review of recent advances in decentralized MARL with networked agents.
problem Sequential decision-making by networked agents without central coordination.
method Analysis of recent algorithms and their theoretical foundations.
result Inspiring more research in this challenging area.
A decentralized MARL algorithm for value propagation in non-linear settings.
problem Decentralized coordination in multi-agent systems with different local rewards.
method Decentralized optimization and value propagation algorithm.
result Non-asymptotic convergence rate of 1/T in nonlinear function approximation.
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.
QTRAN factorizes joint action-value function for cooperative MARL without structural constraints.
problem Value-based solutions for multi-agent reinforcement learning with structural constraints.
method QTRAN: transforming joint action-value function into easily factorizable form.
result QTRAN covers a wider class of MARL tasks than previous methods.
A2C-based MARL controls large-scale traffic signals more efficiently.
problem Scalability issue in centralized RL for large-scale traffic control.
method Decentralized Multi-Agent A2C with improved observability and reduced learning difficulty.
result Optimal, robust, and sample-efficient control over other 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.
GUM tackles MARL by avoiding overestimation through state-marginal restriction.
problem Overestimation of values in large joint state-action spaces.
method Greedy UnMixing through state-marginal restriction and unmixing.
result Superior performance compared to existing Q-learning and general MARL algorithms.
We consider the problem of \emph{fully decentralized} multi-agent reinforcement learning (MARL), where the agents are located at the nodes of a time-varying communication network. Specifically, we assume that the reward functions of the agents might correspond to different tasks, and are only known to the corresponding…
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.
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.
Agents are rewarded for influencing others' actions in MARL, improving coordination and communication.
problem Achieving effective coordination and communication in Multi-Agent Reinforcement Learning.
method Rewarding agents for having causal influence over other agents' actions, assessed through counterfactual reasoning.
result Influence rewards lead to enhanced coordination and communication in challenging social dilemma environments.
Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents. Motivated by decentralized applications such as sensor networks, swarm robotics, and power grids, we study policy evaluation in MARL, where agents with jo…
New algorithm reduces learning regret in multi-agent systems with unknown dynamics.
problem Challenges in decentralized learning due to unknown dynamics and lack of communication.
method Proposed MARL algorithm for two-agent LQ systems with unknown dynamics and one-directional communication.
result Achieved O ( T ) O(\sqrt{T}) O ( T ) regret bound for multi-agent LQ systems with certain communication patterns. This paper improves MARL for networked systems through new protocols and discount factors.
problem Improving control in networked systems using multi-agent reinforcement learning.
method Formulated as a spatiotemporal Markov decision process, introduced a spatial discount factor, and proposed NeurComm.
result Appropriate spatial discount factor enhances learning curves of non-communicative MARL algorithms.
V-learning tackles multiagent reinforcement learning by reducing sample complexity.
problem Curse of multiagents in multiagent reinforcement learning.
method V-learning is a fully decentralized algorithm that learns Nash, correlated, and coarse correlated equilibria.
result V-learning achieves sample complexity that scales with the maximum number of actions per agent, not the joint action space.
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.
This chapter reviews recent advances in multi-agent reinforcement learning.
problem Theoretical foundations for multi-agent reinforcement learning are lacking.
method Selective overview of MARL algorithms with theoretical analysis.
result Identification of new research directions in MARL theory.
A scalable MARL algorithm using local rewards for cooperative multi-agent learning.
problem Scalability issues in cooperative multi-agent reinforcement learning due to large state and action spaces.
method LOMAQ algorithm incorporating local rewards in centralized training and decentralized execution.
result LOMAQ scales well compared to other methods, improving performance and convergence speed.
DSAC improves cooperative MARL with general utilities, converging faster than existing methods.
problem Improving cooperation in multi-agent reinforcement learning with nonlinear utilities.
method Decentralized Shadow Reward Actor-Critic (DSAC) that estimates local occupancy measures and derivatives.
result DSAC converges to ε-stationarity in O(1/ε^2.5) steps with high probability, finding globally optimal policies.
MARL algorithm uses regularization to avoid explicit structures, improving performance.
problem Lack of effective reinforcement learning methods for multi-agent systems.
method MARQ uses regularization to promote structured exploration without explicit centralized structures.
result MARQ outperforms existing methods in multi-agent environments.
QPLEX learns efficient multi-agent Q-values by enforcing IGM principle.
problem Scalable multi-agent reinforcement learning with IGM consistency.
method Dueling duplex network architecture to enforce IGM principle.
result QPLEX achieves high sample efficiency and benefits from offline data.
Decentralized TD learning converges linearly with linear function approximation.
problem Policy evaluation in fully decentralized multi-agent reinforcement learning.
method Temporal-difference learning with linear function approximation, analyzing i.i.d. and Markovian samples.
result Local estimates converge linearly to the optimum under both i.i.d. and Markovian samples.
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.
Hierarchical MARL learns complementary skills for team coordination.
problem Creating intelligent agents that coordinate like human sports teams.
method Two-level hierarchical MARL with unsupervised skill discovery.
result Emergence of useful and complementary skills in team games.
Co-DQL improves traffic signal control using multi-agent reinforcement learning.
problem Optimizing signal timing for large-scale traffic control.
method Cooperative double Q-learning (Co-DQL) with mean field approximation and reward allocation.
result Co-DQL reduces average waiting time for vehicles in the road system.
MARLeME extracts MARL models into symbolic models for better interpretability.
problem Improving interpretability and explainability of MARL systems.
method Develops a MARL model extraction library that approximates MARL systems with symbolic models.
result Enhanced understanding and inspection of MARL systems and agents.
New algorithm tackles multi-agent reinforcement learning issues.
problem Multi-agent reinforcement learning suffers from the curse of many agents.
method Proposes MF-FQI algorithm based on mean embeddings of distributions.
result Establishes a non-asymptotic analysis for MF-FQI algorithm.
QR-MIX models joint state-action values as a distribution to handle randomness in MARL.
problem Randomness in rewards and observations leads to randomness in long-term returns in MARL.
method QR-MIX uses quantile regression and combines it with QMIX and IQN to model joint state-action values as a distribution.
result QR-MIX outperforms QMIX in the StarCraft Multi-Agent Challenge (SMAC) environment.
Paper develops MFC approach to reduce MARL complexity.
problem Curse of dimensionality in cooperative MARL.
method Mean-field control (MFC) and Q-learning.
result Linear convergence rate for MFC-K-Q, independent of N N N . Paper proves efficiency of MARL with transformers, addressing agent complexity.
problem Theoretical understanding of MARL with many agents and limited relational reasoning.
method Set Transformer for relational reasoning, model-free and model-based MARL algorithms.
result Provable efficiency of MARL algorithms, suboptimality gaps independent of number of agents.
A new approach for cooperative multi-agent reinforcement learning with limited communication, reducing the number of communication rounds.
problem Limited communication in decentralized MARL systems leads to outdated information and unstable learning.
method Base policy prediction technique to estimate gradients and collect samples for a sequence of base policies.
result The proposed algorithm converges to an ε-Nash equilibrium with significantly fewer communication rounds and samples.
The paper reviews MARL and its causal challenges, advocating for a 'causality first' approach.
problem Challenges in multi-agent reinforcement learning (MARL) and lack of theoretical guarantees for emergent behavior.
method Discussion of how causal methods can improve safety, interpretability, and robustness in MARL.
result Causal methods can provide strong theoretical guarantees for emergent behavior in MARL.
Adversaries can manipulate cooperative MARL networks.
problem Fragility of consensus-based MARL algorithms to adversarial attacks.
method Study of adversarial attacks on consensus-based MARL networks.
result Consensus-based MARL algorithms are vulnerable to adversarial manipulation.
ABIDES-MARL uses MARL to study market behavior in a realistic financial simulation.
problem Understanding equilibrium behavior in complex financial market games.
method Combines MARL with a realistic LOB simulation to study market behavior.
result Validated approach by solving an extended Kyle model and showing how execution strategies shape market dynamics.
Introduces LTQL for factored policies in cooperative MARL.
problem Learning optimal joint policies in collaborative MARL scenarios.
method Logical Team Q-learning (LTQL) as a stochastic approximation to dynamic programming.
result LTQL provides factored policies for optimal joint behavior in cooperative MARL.
Efficient communication improves MARL performance in StarCraft II.
problem Achieving efficient communication among agents in multi-agent reinforcement learning.
method Variance Based Control (VBC) to limit message variance and preserve useful information.
result VBC reduces communication overhead by 2-10 times compared to state-of-the-art MARL algorithms.
Study compares MAPF and MARL algorithms for warehouse automation.
problem Optimizing multi-agent pickup and delivery in warehouse settings.
method Compared conflict-based search (MAPF) and shared experience actor-critic (MARL).
result Comprehensive benchmarking of MAPF and MARL in a simulated warehouse environment.
New methods improve multi-agent reinforcement learning by addressing rotational dynamics.
problem Reproducibility crisis in multi-agent reinforcement learning.
method Reframing MARL approaches using Variational Inequalities (VIs) and proposing gradient-based VI methods.
result Significant performance improvements across benchmarks, including better convergence to equilibrium strategies in zero-sum games.
This work improves MARL exploration efficiency using predictive guidance and prioritized experience replay.
problem Challenges in multi-agent reinforcement learning, especially in exploration efficiency and reward informativeness.
method A predictive network forecasts reward, guiding MARL to accelerate exploration. Improved prioritized experience replay utilizes TD error effectively.
result The proposed algorithm outperforms existing methods in cooperative multi-agent environments.
AEC Games model represents software MARL environments better than POSGs.
problem POSGs are conceptually unsuitable for software MARL environments.
method Introduced AEC Games model as an equivalent to POSGs.
result AEC Games model is more representative of software MARL environments.
Paper proposes a voting-based MARL approach for IoT systems.
problem Maximizing globally averaged returns in multi-agent IoT systems.
method Formulated as linear programming, proposed distributed primal-dual algorithm, voting mechanism for convergence.
result Distributed learning achieves sublinear convergence rate similar to centralized learning.
This review covers recent cooperative MARL approaches and their challenges.
problem Recent progress in multi-agent reinforcement learning (MARL).
method Five common approaches: independent learners, fully observable critic, value function factorization, consensus, and learn to communicate.
result Challenges and solutions for each approach are discussed.
PettingZoo library accelerates multi-agent reinforcement learning research.
problem Challenges in multi-agent reinforcement learning, especially conceptual models of games.
method Developed PettingZoo library with AEC games model to address multi-agent reinforcement learning challenges.
result AEC games model addresses conceptual issues in multi-agent reinforcement learning environments.
MARL improves LBM stability and accuracy across scales.
problem Stability and accuracy issues in under-resolved LBM simulations.
method Multi-Agent Reinforcement Learning (MARL) to dynamically control local relaxation parameters.
result MARL closures stabilize simulations and recover spectra of fully resolved models.
ReF-ER algorithm improved performance in multi-agent reinforcement learning.
problem Improving performance in multi-agent reinforcement learning environments.
method Extended ReF-ER algorithm to include dependencies between agents and modeled environment dynamics.
result ReF-ER MARL outperforms state-of-the-art algorithms in collaborative environments.
EMIX minimizes surprise in multi-agent reinforcement learning.
problem Surprise and approximation bias in multi-agent reinforcement learning.
method Energy-based MIXer (EMIX) for minimizing surprise across multiple agents.
result EMIX demonstrates consistent stable performance in challenging StarCraft II scenarios.