Solving tasks with sparse rewards is a main challenge in reinforcement
l...
Planning has been very successful for control tasks with known environme...
Humans have a remarkable ability to use physical commonsense and predict...
Obtaining reliable uncertainty estimates of neural network predictions i...
What is a good visual representation for autonomous agents? We address t...
We present PRM-RL, a hierarchical method for long-range navigation task
...
We introduce TensorFlow Agents, an efficient infrastructure paradigm for...
This paper focuses on the problem of learning 6-DOF grasping with a para...
Domain knowledge can often be encoded in the structure of a network, suc...
We propose ThalNet, a deep learning model inspired by neocortical
commun...
It has long been assumed that high dimensional continuous control proble...
Deep neural networks coupled with fast simulation and improved computati...
We introduce a neural architecture for navigation in novel environments....
There has been a recent paradigm shift in robotics to data-driven learni...