Domain-incremental learning
Domain-incremental learning involves training machine learning models to adapt to new domains while retaining knowledge from previous ones.
domain adaptation
Source-free domain adaptation
Source-free domain adaptation is a method in machine learning that adapts models to new domains without requiring labeled data from the original source domain.
Domain adaptation (machine learning)
Domain adaptation is a subfield of machine learning focused on adapting models trained on one domain to perform well on a different but related domain.
Cycle-consistency for imitation
Cycle-consistency for imitation is a technique in machine learning and artificial intelligence that ensures an agent can imitate expert behavior by enforcing a bidirectional consistency constraint. This method improves learning stability and performance in imitation tasks by requiring the agent’s outputs to be consistent when mapped back and forth between different domains or representations.
Sim-to-real transfer for RL
Sim-to-real transfer for reinforcement learning (RL) involves adapting models trained in simulation to perform in real-world environments, addressing challenges like domain gaps.