Method, device and computer program for producing a strategy for a robot

A method, comprising:

• producing a strategy for an agent so that a specifiable goal is reached when the agent performs actions based on the strategy, depending on a respective situation, strategy being produced by:
• initializing the strategy and an episode length;
• repeatedly executing a loop including the steps:
• producing a plurality of further strategies as a function of the strategy;
• applying the plurality of the further strategies for a respective at least one episode having the episode length;
• ascertaining, for each of the further strategies, a respective cumulative reward which is obtained when applying the respective further strategy;
• updating the strategy as a function of a specifiable number of the further strategies that obtained the greatest respective cumulative rewards;
• wherein the episode length is increased following each execution of the loop;
• and
• using a trained neural network for providing an action corresponding to the produced strategy as a function of a current state of the agent and/or a current state of an environment of the agent provided to the neural network, the produced strategy being implemented by the neural network in that the neural network provides the action corresponding to the produced strategy from a state provided to the neural network.

A non-transitory machine-readable memory element on which is stored a computer program for producing a strategy for an agent so that a specifiable goal is reached when the agent performs actions based on the strategy, depending on a respective situation, the computer program, when executed by a computer, causing the computer to perform the following steps:

• initializing the strategy and an episode length;
• repeatedly executing a loop including the steps:
• producing a plurality of further strategies as a function of the strategy;
• applying the plurality of the further strategies for a respective at least one episode having the episode length;
• ascertaining, for each of the further strategies, a respective cumulative reward which is obtained when applying the respective further strategy;
• updating the strategy as a function of a specifiable number of the further strategies that obtained the greatest respective cumulative rewards;
• wherein the episode length is increased following each execution of the loop.

A device configured to produce a strategy for an agent so that a specifiable goal is reached when the agent performs actions based on the strategy, depending on a respective situation, the device configured to:

• initialize the strategy and an episode length;
• repeatedly execute a loop including:
• producing a plurality of further strategies as a function of the strategy;
• applying the plurality of the further strategies for a respective at least one episode having the episode length;
• ascertaining, for each of the further strategies, a respective cumulative reward which is obtained when applying the respective further strategy;
• and
• updating the strategy as a function of a specifiable number of the further strategies that obtained the greatest respective cumulative rewards;
• wherein the episode length is increased following each execution of the loop.