In this work, we introduce a scalable Bayesian causal discovery framework based on a combination of stochastic gradient Markov Chain Monte Carlo (SG-MCMC) and V ariational Inference (VI) that overcomes these limitations.

In this paper, we investigate integrating this inductive bias of sparse interactions into thelatent dynamics ofworld models trained from pixels.

Much ofreinforcement learning theory isbuiltontopoforacles that arecomputationally hard to implement.