Offline Reinforcement Learning via Tsallis Regularization.
Lingwei ZhuMatthew SchlegelHan WangMartha WhitePublished in: Trans. Mach. Learn. Res. (2024)
Keyphrases
- reinforcement learning
- function approximation
- information theory
- reinforcement learning algorithms
- learning algorithm
- multi agent
- learning process
- model free
- optimal control
- parameter selection
- state space
- data dependent
- markov decision processes
- autonomous learning
- smoothing parameter
- multi agent reinforcement learning
- real time
- regularization parameter
- supervised learning
- temporal difference
- blind deconvolution
- function approximators
- optimal policy
- policy search
- machine learning