From Reward to Histone: Combining Temporal-Difference Learning and Epigenetic Inheritance for Swarm's Coevolving Decision Making.
Faqihza MukhlishJohn PageMichael BainPublished in: ICDL-EPIROB (2020)
Keyphrases
- temporal difference learning
- reinforcement learning
- decision making
- function approximation
- fixed point
- game playing
- approximate value iteration
- temporal difference
- reinforcement learning algorithms
- particle swarm optimization
- evaluation function
- search space
- learning algorithm
- markov decision process
- supply chain
- monte carlo
- markov decision processes
- dynamical systems
- neural network
- graphical models
- evolutionary algorithm
- artificial neural networks
- machine learning