A Distributed-GPU Deep Reinforcement Learning System for Solving Large Graph Optimization Problems.
Weijian ZhengDali WangFengguang SongPublished in: ACM Trans. Parallel Comput. (2023)
Keyphrases
- optimization problems
- reinforcement learning
- combinatorial optimization
- distributed sensor networks
- multi agent
- evolutionary algorithm
- nonlinear programming
- real time
- metaheuristic
- cooperative
- cost function
- distributed constraint satisfaction problems
- distributed systems
- action selection
- state space
- graph model
- graph theory
- reinforcement learning algorithms
- optimization methods
- weighted graph
- function approximation
- temporal difference
- machine learning
- dynamic programming
- random walk
- graph representation
- spanning tree
- parallel implementation
- distributed environment
- traveling salesman problem
- graph structure
- graph matching
- data transfer
- peer to peer
- graphics hardware
- parallel processing
- markov decision problems
- constrained problems
- social networks
- distributed constraint satisfaction
- bipartite graph