DPPO with Summed Likelihood (QSM-PG)#13

Open

jlidard wants to merge 7 commits intomainfrom

dppo_sumlikelihood

Commits on Nov 15, 2024

add diffusion versions of rlpd/ibrl/cal-ql
Justin M. Lidard
committed
fix typo:
Justin M. Lidard
committed
config fix
Justin M. Lidard
committed
make forward pass differentiable
Justin M. Lidard
committed

Commits on Nov 22, 2024

update configs
Justin M. Lidard
committed

Commits on Nov 23, 2024

add ppo with summed likelihood
Justin M. Lidard
committed
minor
Justin M. Lidard
committed