Reward Shaping-Based Actor-Critic Deep Reinforcement Learning for Residential Energy Management.
Renzhi LuZhenyu JiangHuaming WuYuemin DingDong WangHai-Tao ZhangPublished in: IEEE Trans. Ind. Informatics (2023)
Keyphrases
- reward shaping
- actor critic
- energy management
- reinforcement learning
- energy saving
- reinforcement learning algorithms
- temporal difference
- energy consumption
- power consumption
- policy gradient
- state space
- approximate dynamic programming
- markov decision processes
- function approximation
- optimal control
- model free
- machine learning
- learning algorithm
- wireless sensor networks
- multi agent
- dynamic programming
- policy iteration
- reinforcement learning methods
- transfer learning
- neural network
- complex domains
- partially observable
- function approximators
- reward function
- multi agent systems
- action selection
- learning agent
- markov decision problems
- mobile robot
- optimal policy