World Model Benefits
Marc and Mark discuss the benefits of separating dynamics and reward in world models. They highlight how agents can generalize tasks by superimposing different reward functions on shared dynamics, leading to quicker learning in new environments. Tim Scarfe reflects on the evolution of robust models through domain perturbations and reward-free exploration.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Can we build a generalist agent? Dr. Minqi Jiang and Dr. Marc Rigter
Related Questions