Although reinforcement learning has seen remarkable progress over the last years, solving robust dexterous object-manipulation tasks in multi-object settings remains a challenge.
An important component for generalization in machine learning is to uncover underlying latent factors of variation as well as the mechanism through which each factor acts in the world.
By training 240 representations and over 10, 000 reinforcement learning (RL) policies on a simulated robotic setup, we evaluate to what extent different properties of pretrained VAE-based representations affect the OOD generalization of downstream agents.
; and (ii) if the new predictions differ from the current ones, should we update?
Learning data representations that are useful for various downstream tasks is a cornerstone of artificial intelligence.
Coupled with a suitable interpolation procedure this offers an accurate and computationally efficient technique for simulating partially ionised air plasma.
Computational Physics Applied Physics Fluid Dynamics Plasma Physics
Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning.
To facilitate research addressing this problem, we propose CausalWorld, a benchmark for causal structure and transfer learning in a robotic manipulation environment.
The focus of disentanglement approaches has been on identifying independent factors of variation in data.