概念导读
Multi-Task Learning (MTL) is a learning paradigm where a single model is trained to perform multiple tasks simultaneously, leveraging shared representations to improve generalization. In the context of policy-distillation, multi-task learning is relevant because distillation often involves transferring capabilities across multiple tasks or domains to a singl...
- Related
- References
Multi-Task Learning
Multi-Task Learning (MTL) is a learning paradigm where a single model is trained to perform multiple tasks simultaneously, leveraging shared representations to improve generalization. In the context of policy-distillation, multi-task learning is relevant because distillation often involves transferring capabilities across multiple tasks or domains to a single student model.
Related
- policy-distillation — Policy distillation naturally handles multi-task scenarios
- multi-domain-on-policy-distillation — Extension of OPD to multi-domain settings