A Centralised Soft Actor Critic Deep Reinforcement Learning Approach to District Demand Side Management through CityLearn.
Anjukan KathirgamanathanKacper TwardowskiEleni E. ManginaDonal FinnPublished in: CoRR (2020)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- temporal difference
- optimal control
- reinforcement learning algorithms
- approximate dynamic programming
- neuro fuzzy
- function approximation
- policy iteration
- gradient method
- model free
- state space
- policy gradient methods
- natural actor critic
- markov decision processes
- learning algorithm
- average reward
- rl algorithms
- optimal policy
- machine learning
- supervised learning
- transfer learning
- partially observable markov decision processes
- markov chain
- dynamic environments
- action selection
- monte carlo
- mobile robot
- dynamic programming
- decision making
- linear program