Orientation-Preserving Rewards' Balancing in Reinforcement Learning.
Jinsheng RenShangqi GuoFeng ChenPublished in: IEEE Trans. Neural Networks Learn. Syst. (2022)
Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- model free
- state space
- temporal difference
- reinforcement learning algorithms
- multi agent
- reward shaping
- machine learning
- supervised learning
- reward function
- learning algorithm
- gabor filters
- robotic control
- policy search
- hidden state
- learning problems
- genetic algorithm