Reinforced learning method and device based on short-time access mechanism and storage medium

Abstract

The invention relates to a reinforcement learning method and device based on a short-time access mechanism, and a storage medium. The method comprises the steps: configuring a state cache list which is used for storing state increment information obtained through the change of a current environment state of an intelligent agent under the condition that the intelligent agent meets a preset short-time access mechanism; inputting all actions of the intelligent agent at the next moment into the environment state transition probability model, and outputting a plurality of environment states of allactions corresponding to the next moment; comparing the plurality of environment states at the next moment with the state increment information in the state cache list, and determining an action corresponding to the environment state with the maximum difference in the plurality of environment states as a first alternative action executed by the intelligent agent at the next moment; and executing exploration operation for reinforcement learning according to the first alternative action. According to the invention, through the state cache list, repeated exploration of the explored environment state is avoided; through the environment state transition probability model, the exploration of the intelligent agent to the unknown state is strengthened and guided, and the learning efficiency is effectively improved.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, and in particular to a reinforcement learning method, device and storage medium based on a short-term access mechanism. Background technique [0002] Reinforcement learning refers to a learning method that controls the interaction between an agent (agent) and the environment in order to enable the agent to obtain the maximum reward in the environment. One of the most important problems faced in reinforcement learning is how to trade off "exploration" and "exploitation": too much reliance on "exploration" will reduce the learning efficiency of the agent's action strategy, and too much reliance on "exploitation" "It will cause the agent to be unable to learn more effective action strategies; relying solely on "exploration" or "utilization" cannot complete reinforcement learning tasks well. Traditional solutions usually use a count-based method, that is, maintain a global s...

AI Technical Summary

Problems solved by technology

[0003] In view of this, this disclosure proposes a reinforcement learning technical solution based on a short-term access mechanism to solve the problem of low learning efficiency of the agent's action strategy in the reinforcement learning process

Images