Multi-agent natural actor-critic reinforcement learning algorithms
From MaRDI portal
Publication:6159507
DOI10.1007/s13235-022-00449-9zbMath1519.91063arXiv2109.01654OpenAlexW3198538443MaRDI QIDQ6159507
Nandyala Hemachandra, Prashant Trivedi
Publication date: 20 June 2023
Published in: Dynamic Games and Applications (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2109.01654
Fisher information matrixnon-convex optimizationstochastic approximationsnetworked agentsfunction approximationsactor-critic methodsalgorithms for better local minimalocal optima value comparisonnatural gradientsquasi second-order methodstraffic network control
Traffic problems in operations research (90B20) Distributed algorithms (68W15) Algorithmic game theory and complexity (91A68)
Related Items
Cites Work
- Natural actor-critic algorithms
- Stochastic approximation methods for constrained and unconstrained systems
- Multi-agent reinforcement learning: a selective overview of theories and algorithms
- Nonlinear Gossip
- OnActor-Critic Algorithms
- Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
- Optimization Methods for Large-Scale Machine Learning
- The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
- Distributed Subgradient Methods for Multi-Agent Optimization
- Finite-Time Performance of Distributed Temporal-Difference Learning with Linear Function Approximation
- A Concentration Bound for Stochastic Approximation via Alekseev’s Formula
- Information Flow and Cooperative Control of Vehicle Formations
- Performance of a Distributed Stochastic Approximation Algorithm
- Separability, neutrality and certainty equivalence†
- Adjustment of an Inverse Matrix Corresponding to a Change in One Element of a Given Matrix
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
