Predictive PER: Balancing Priority and Diversity towards Stable Deep Reinforcement Learning.
Sanghwa LeeJaeyoung LeeIchiro HasuoPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- partially observable
- model free
- markov decision processes
- optimal policy
- data sets
- reinforcement learning algorithms
- predictive model
- learning process
- dynamic programming
- policy search
- autonomous learning
- deep learning
- temporal difference
- machine learning
- optimal control
- multi agent
- state space
- learning algorithm
- case study
- neural network
- real time
- supervised learning
- predictive modeling
- temporal difference learning
- multi agent reinforcement learning
- active learning
- robotic control