Offline reinforcement learning
4 methods in the atlas attack this one problem. They are rivals: each wins something the others do not.
Phrasings that mean this problem
Offline RL
reinforcement-learning
- Conservative Q-learningOut-of-distribution penaltyspecialistreinforcement-learning
- Batch-constrained Q-learningstandalonespecialistreinforcement-learning
- Implicit Q-learningExpectile regressionspecialistreinforcement-learning
- Decision transformerReturn-conditioned sequencesspecialistreinforcement-learning