November 18, 2019
Cross Roads was proud to host David Ha of Google Brain. David gave us an overview of his paper "Learning to Predict Without Looking Ahead: World Models Without Forward Prediction".
According to David Ha, of Google Brian, much of model-based reinforcement learning involves learning a model of an agent’s world and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every naturally occurring model of the world of which we are aware – e.g., a brain – arose as a byproduct of competing evolutionary pressures for survival, not minimization of a supervised forward-predictive loss via gradient descent. That useful models can arise out of the messy and slow optimization process of evolution suggests that forward-predictive modeling can arise as a side-effect of optimization under the right circumstances.
Read the full summary here.