Google Inc.

X Development LLC

Karol Hausman

Mrinal Kalakrishnan

Alexander Toshev

Seyed Mohammad Khansari Zadeh

Peter Pastor Sampedro

Adrian Li

Soeren Pirk

Cristian Bodnar

Training and/or using a machine learning model for performing robotic tasks is disclosed herein. In many implementations, an environment-conditioned action sequence prediction model is used to determine a set of actions as well as a corresponding particular order for the actions for the robot to perform to complete the task. In many implementations, each action in the set of actions has a corresponding action network used to control the robot in performing the action.

Determining environment-conditioned action sequences for robotic tasks

Techniques are described herein for robotic control using value distributions. In various implementations, as part of performing a robotic task, state data associated with the robot in an environment may be generated based at least in part on vision data captured by a vision component of the robot. A plurality of candidate actions may be sampled, e.g., from continuous action space. A trained critic neural network model that represents a learned value function may be used to process a plurality of state-action pairs to generate a corresponding plurality of value distributions. Each state-action pair may include the state data and one of the plurality of sampled candidate actions. The state-action pair corresponding to the value distribution that satisfies one or more criteria may be selected from the plurality of state-action pairs. The robot may then be controlled to implement the sampled candidate action of the selected state-action pair.

Robotic control using value distributions

Growing community of inventors

Mountain View, CA, United States of America

Karol Hausman