Neuro-Inspired Reinforcement Learning to Improve Trajectory Prediction in Reward-Guided Behavior.
Bo-Wei ChenShih-Hung YangChao-Hung KuoJia-Wei ChenYu-Chun LoYun-Ting KuoYi-Chen LinHao-Cheng ChangSheng-Huang LinXiao YuBoyi QuShuan-Chu Vina RoHsin-Yi LaiYou-Yin ChenPublished in: Int. J. Neural Syst. (2022)
Keyphrases
- reinforcement learning
- prediction accuracy
- neural network
- eligibility traces
- improve the prediction accuracy
- multi agent
- function approximation
- prediction algorithm
- machine learning
- state space
- optimal policy
- model free
- reinforcement learning algorithms
- average reward
- dynamic programming
- learning algorithm
- action selection
- temporal difference
- initially unknown
- data sets