公开(公告)号：US20240320506A1

公开(公告)日：2024-09-26

申请号：US18698890

申请日：2022-10-05

申请人： DeepMind Technologies Limited

发明人： Anirudh Goyal ,  Andrea Banino ,  Abram Luke Friesen ,  Theophane Guillaume Weber ,  Adrià Puigdomènech Badia ,  Nan Ke ,  Simon Osindero ,  Timothy Paul Lillicrap ,  Charles Blundell

IPC分类号： G06N3/092 ,  G06N3/044 ,  G06N3/0455 ,  G06N3/084

CPC分类号： G06N3/092 ,  G06N3/044 ,  G06N3/0455 ,  G06N3/084

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling a reinforcement learning agent in an environment to perform a task using a retrieval-augmented action selection process. One of the methods includes receiving a current observation characterizing a current state of the environment; processing an encoder network input comprising the current observation to determine a policy neural network hidden state that corresponds to the current observation; maintaining a plurality of trajectories generated as a result of the reinforcement learning agent interacting with the environment; selecting one or more trajectories from the plurality of trajectories; updating the policy neural network hidden state using update data determined from the one or more selected trajectories; and processing the updated hidden state using a policy neural network to generate a policy output that specifies an action to be performed by the agent in response to the current observation.

公开(公告)号：US20240256884A1

公开(公告)日：2024-08-01

申请号：US18424687

申请日：2024-01-26

申请人： DeepMind Technologies Limited

发明人： Hado Philip van Hasselt ,  Nan Ke ,  Chentian Jiang

IPC分类号： G06N3/092 ,  G06N3/042

CPC分类号： G06N3/092 ,  G06N3/042

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent interacting with an environment to perform a task. In one aspect, one of the methods include: maintaining context data; receiving a current observation characterizing a current state of the environment; generating a current graph model that represents the environment; selecting, from a possible set of actions and using the current graph model, a current action to be performed by the agent in response to the current observation; controlling the agent to perform the selected current action to cause the environment to transition from the current state into a new state; and updating the context data to include (i) data identifying the selected current action and (ii) a new observation characterizing the new state of the environment.