Deepmind Technologies Limited

Gdm Holding LLC

Martin Riedmiller

Nicolas Manfred Otto Heess

Mel Vecerik

Thomas Lampe

Roland Hafner

Timothy Paul Lillicrap

Gabriel Barth-Maron

Ivaylo Popov

Jonathan Karl Scholz

Bilal Piot

Olivier Claude Pietquin

Thomas Rothoerl

Todd Andrew Hester

Wang Fumin

Tim Hertweck

Markus Wulfmeier

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment to accomplish a goal. In one aspect, a method comprises: obtaining an observation characterizing a state of the environment, processing the observation using an embedding model to generate a lower-dimensional embedding of the observation, determining an auxiliary task reward based on a value of a particular dimension of the embedding, determining an overall reward based at least in part on the auxiliary task reward, and determining an update to values of multiple parameters of an action selection neural network based on the overall reward using a reinforcement learning technique.

Training action selection neural networks using auxiliary tasks of controlling observation embeddings

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-efficient reinforcement learning. One of the systems is a system for training an actor neural network used to select actions to be performed by an agent that interacts with an environment by receiving observations characterizing states of the environment and, in response to each observation, performing an action selected from a continuous space of possible actions, wherein the actor neural network maps observations to next actions in accordance with values of parameters of the actor neural network, and wherein the system comprises: a plurality of workers, wherein each worker is configured to operate independently of each other worker, wherein each worker is associated with a respective agent replica that interacts with a respective replica of the environment during the training of the actor neural network.

Data-efficient reinforcement learning for continuous control tasks

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning with scheduled auxiliary tasks. In one aspect, a method includes maintaining data specifying parameter values for a primary policy neural network and one or more auxiliary neural networks; at each of a plurality of selection time steps during a training episode comprising a plurality of time steps: receiving an observation, selecting a current task for the selection time step using a task scheduling policy, processing an input comprising the observation using the policy neural network corresponding to the selected current task to select an action to be performed by the agent in response to the observation, and causing the agent to perform the selected action.

Reinforcement learning with scheduled auxiliary control

An off-policy reinforcement learning actor-critic neural network system configured to select actions from a continuous action space to be performed by an agent interacting with an environment to perform a task. An observation defines environment state data and reward data. The system has an actor neural network which learns a policy function mapping the state data to action data. A critic neural network learns an action-value (Q) function. A replay buffer stores tuples of the state data, the action data, the reward data and new state data. The replay buffer also includes demonstration transition data comprising a set of the tuples from a demonstration of the task within the environment. The neural network system is configured to train the actor neural network and the critic neural network off-policy using stored tuples from the replay buffer comprising tuples both from operation of the system and from the demonstration transition data.

Training action selection neural networks using apprenticeship

Growing community of inventors

Balgheim, Germany

Martin Riedmiller