Deepmind Technologies Limited

William Clinton Dabney

Georg Ostrovski

Marc Gendron-Bellemare

Razvan Pascanu

Tom Schaul

Simon Osindero

Fengning Ding

Diana Luiza Borsa

David Szepesvari

Thomas Stepleton

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting an action to be performed by a reinforcement learning agent interacting with an environment. In one aspect, a method comprises: receiving a current observation; for each action of a plurality of actions: randomly sampling one or more probability values; for each probability value: processing the action, the current observation, and the probability value using a quantile function network to generate an estimated quantile value for the probability value with respect to a probability distribution over possible returns that would result from the agent performing the action in response to the current observation; determining a measure of central tendency of the one or more estimated quantile values; and selecting an action to be performed by the agent in response to the current observation using the measures of central tendency for the actions.

Distributional reinforcement learning using quantile function neural networks

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes sampling a behavior modulation in accordance with a current probability distribution; for each of one or more time steps: processing an input comprising an observation characterizing a current state of the environment at the time step using an action selection neural network to generate a respective action score for each action in a set of possible actions that can be performed by the agent; modifying the action scores using the sampled behavior modulation; and selecting the action to be performed by the agent at the time step based on the modified action scores; determining a fitness measure corresponding to the sampled behavior modulation; and updating the current probability distribution over the set of possible behavior modulations using the fitness measure corresponding to the behavior modulation.

Modulating agent behavior to optimize learning progress

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting an action to be performed by a reinforcement learning agent interacting with an environment. A current observation characterizing a current state of the environment is received. For each action in a set of multiple actions that can be performed by the agent to interact with the environment, a probability distribution is determined over possible Q returns for the action-current observation pair. For each action, a measure of central tendency of the possible Q returns with respect to the probability distributions for the action-current observation pair is determined. An action to be performed by the agent in response to the current observation is selected using the measures of central tendency.

Distributional reinforcement learning

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing and storing inputs for use in a neural network. One of the methods includes receiving input data for storage in a memory system comprising a first set of memory blocks, the memory blocks having an associated order; passing the input data to a highest ordered memory block; for each memory block for which there is a lower ordered memory block: applying a filter function to data currently stored by the memory block to generate filtered data and passing the filtered data to a lower ordered memory block; and for each memory block: combining the data currently stored in the memory block with the data passed to the memory block to generate updated data, and storing the updated data in the memory block.

Growing community of inventors

London, United Kingdom

William Clinton Dabney