You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This issue arises when I implement the LocalSearchSampler, especially the Metropolis-Hastings (MH) rule.
In short, we need both the log_pbs and log_pfs of each trajectory $\tau_{bwd}=(x\to\cdots s' \cdots \to s_0)$ and $\tau_{recon}=(s_0 \to \cdots s' \cdots \to x')$ for MH (see this!).
There are two issues here.
Trajectory reversion may be needed for simpler computation of log_pfs($\tau_{bwd}$) - Check the related comment
It's hard to calculate log_pbs and log_pfs within current structure (TrajectoryBasedGFlowNet has method get_pfs_and_pbs, but Sampler can't access to it) - Check the related comments.
The text was updated successfully, but these errors were encountered:
This issue arises when I implement the
LocalSearchSampler
, especially the Metropolis-Hastings (MH) rule.In short, we need both the$\tau_{bwd}=(x\to\cdots s' \cdots \to s_0)$ and $\tau_{recon}=(s_0 \to \cdots s' \cdots \to x')$ for MH (see this!).
log_pbs
andlog_pfs
of each trajectoryThere are two issues here.
log_pbs
andlog_pfs
within current structure (TrajectoryBasedGFlowNet
has methodget_pfs_and_pbs
, butSampler
can't access to it) - Check the related comments.The text was updated successfully, but these errors were encountered: