world2vec learns mechanistic world models from observations and actions
Latent dynamics use at least ten times fewer parameters than DreamerV3, TD-MPC2 and LeWM, without reward.
42
Latent dynamics use at least ten times fewer parameters than DreamerV3, TD-MPC2 and LeWM, without reward.
A linear 64-dimensional recurrent memory matches DreamerV3 and GRU on simulated air-hockey defence under tracking loss.
Today 1.8K readers · 4.3K views · 3.2K reads · all time 162K views