A Comparative Study of Reinforcement Learning Algorithms for Distribution Network Reconfiguration With Deep Q-Learning-Based Action Sampling.
Nastaran GholizadehNazli KazemiPetr MusilekPublished in: IEEE Access (2023)
Keyphrases
- reinforcement learning algorithms
- distribution network
- reinforcement learning
- reward shaping
- model free
- state space
- markov decision processes
- ant colony algorithm
- traveling salesman problem
- artificial fish
- reinforcement learning problems
- eligibility traces
- reinforcement learning methods
- temporal difference
- learning algorithm
- action selection
- supply chain
- particle swarm
- action space
- power distribution networks
- function approximation
- monte carlo
- state action
- stochastic games
- reward function
- optimal policy
- multiagent reinforcement learning
- mobile robot
- dynamic programming
- dynamic environments
- combinatorial optimization
- evolutionary algorithm
- function approximators
- agent learns
- policy search
- ant colony optimization