Reframing Offline Reinforcement Learning as a Regression Problem.
Prajwal KoiralaCody H. FlemingPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- regression model
- function approximation
- state space
- reinforcement learning algorithms
- linear regression
- learning algorithm
- temporal difference
- regression problems
- robotic control
- real time
- regression algorithm
- aggregating algorithm
- regression method
- learning process
- simple linear
- polynomial regression
- model free
- support vector regression
- optimal policy
- model selection
- multi agent
- regression analysis
- machine learning
- markov decision processes
- partial least squares
- ridge regression
- regression function
- support vector
- locally weighted
- temporal difference learning
- classification and regression problems
- autonomous learning
- artificial neural networks
- optimal control
- action selection