SUF: Stabilized Unconstrained Fine-Tuning for Offline-to-Online Reinforcement Learning.
Jiaheng FengMingxiao FengHaolin SongWengang ZhouHouqiang LiPublished in: AAAI (2024)
Keyphrases
- fine tuning
- reinforcement learning
- real time
- fine tune
- viable alternative
- fine tuned
- learning algorithm
- online learning
- machine learning
- database
- learning process
- function approximation
- data sets
- recognition rate
- transfer learning
- markov decision processes
- reinforcement learning algorithms
- batch mode
- temporal difference learning
- stochastic approximation
- databases