subtb_loss.hpp File Reference

GFlowNet SubTB(lambda) loss (Madan et al., "Learning GFlowNets from partial episodes for improved convergence and stability", arXiv:2209.12782). More...

Go to the source code of this file.

Classes
class	pulsatrix::SubTBLoss
	One sub-trajectory pair's contribution to the SubTB(λ) loss: Δ(i,j) = log F(s_i) + Σ log P_F − log F(s_j) − Σ log P_B (summed over the edges spanned by [i,j)), weighted by ‘pair_weight_ratio = λ^{j-i} / Σ_{i’<j'} λ^{j'-i'}` (the pre-normalized share of the total weighted-average loss this specific pair contributes). More...

Namespaces
namespace	pulsatrix

Detailed Description

GFlowNet SubTB(lambda) loss (Madan et al., "Learning GFlowNets from partial episodes for improved convergence and stability", arXiv:2209.12782).