概念导读
Ex-OPD (Extended/Extrapolated On-Policy Distillation) is a variant of on-policy distillation that extends the OPD framework with reward extrapolation capabilities. Referenced in the context of generalized-on-policy-distillation, Ex-OPD explores how on-policy methods can be augmented with additional reward signals beyond standard teacher feedback.
- Related
- References
Ex-OPD
Ex-OPD (Extended/Extrapolated On-Policy Distillation) is a variant of on-policy distillation that extends the OPD framework with reward extrapolation capabilities. Referenced in the context of generalized-on-policy-distillation, Ex-OPD explores how on-policy methods can be augmented with additional reward signals beyond standard teacher feedback.
Related
- generalized-on-policy-distillation — G-OPD framework that introduces reward extrapolation to OPD
- on-policy-distillation — Core OPD concept