Reinforcement learning strategy learning method based on potential action representation space

Abstract

Sample utilization rate and learning efficiency are an important bottleneck problem of deep reinforcement learning in practical application. For the real world, in order to quickly and accurately obtain a universal strategy, the invention provides a reinforcement learning strategy learning method based on a potential action representation space, and the method learns the strategy in the potentialspace of the action and maps the action representation to the real action space; a strategy in the method is mapping from a state to action representation, the search space of strategy learning can bereduced, and the strategy learning efficiency is improved; according to the method, mature supervised learning can be selected for offline learning for representation of actions, the learning speed can be further increased, and the stability is improved. Besides, as long as the characteristics of the adopted actions are similar, even for tasks different from the training strategy, the learned strategy can be generalized into the action space of the current execution task under the fine tuning of a small number of learning samples, and the generalization ability of strategy expression is greatly improved.

Description

technical field [0001] The present invention relates to the field of machine learning, and more specifically relates to a reinforcement learning strategy learning method based on latent action representation space. Background technique [0002] Deep reinforcement learning achieves direct control from input to output through end-to-end learning, enabling reinforcement learning to be extended to decision-making problems with high-dimensional state and action spaces that were previously difficult to deal with. Technical support has become a research hotspot that has attracted much attention. So far, deep reinforcement learning has been successfully applied to many fields: such as robotics, games, parameter optimization, video prediction, machine translation, automatic driving, intelligent transportation systems, multi-agent systems, aerospace systems and digital art intelligent systems, etc. [0003] An important prerequisite for the success of deep reinforcement learning is a...

AI Technical Summary

Problems solved by technology

However, for complex intelligent systems in practical applications, it takes a lot of time and money to collect sufficient learning samples, and there is even a risk of damaging the intelligent system. For example, collecting learning samples of robots performing tasks in dangerous environments may cause mechanical injury

It can be seen that the sample utilization rate and learning efficiency are an important bottleneck in the practical application of deep reinforcement learning.

Images