Open josephdviviano opened 9 months ago
When using a conditional gflownet, we need the LogZ estimate (in algorithms such as TB) to be conditional, i.e., predicted from the state.
This means the logz parameter must not be constrained to be a single parameter.
logz
Also, for conditional generation, sampling should accept an instance and/or iterator optionally, to condition on.
When using a conditional gflownet, we need the LogZ estimate (in algorithms such as TB) to be conditional, i.e., predicted from the state.
This means the
logz
parameter must not be constrained to be a single parameter.Also, for conditional generation, sampling should accept an instance and/or iterator optionally, to condition on.