We introduce a simple but effective method for managing risk in model-ba...
Inverse design refers to the problem of optimizing the input of an objec...
There has been significant recent progress in the area of unsupervised s...
To avoid failures on out-of-distribution data, recent works have sought ...
Learning diverse skills is one of the main challenges in robotics. To th...
Learning agile skills is one of the main challenges in robotics. To this...
Embedding discrete solvers as differentiable layers has given modern dee...
Utilizing amortized variational inference for latent-action reinforcemen...
Although model-based and model-free approaches to learning the control o...
Rank-based metrics are some of the most widely used criteria for perform...
Achieving fusion of deep learning with combinatorial algorithms promises...