Inverse reinforcement learning processing method and device, storage medium and electronic device

Abstract

The embodiment of the invention provides an inverse reinforcement learning processing method and device, a storage medium and an electronic device, and the method comprises the steps of obtaining a target demonstration track which is provided by taking a target state in a preset state candidate set as an initial state; adding the target demonstration track into the initialized demonstration set to obtain an updated demonstration set; and performing inverse reinforcement learning training according to the updated demonstration set to obtain a target strategy meeting a preset condition. According to the invention, the problem of high cost caused by a large number of expert demonstration due to the need of collecting a large number of expert demonstration in inverse reinforcement learning in related technologies can be solved; comprising selecting a most valuable state (a target state with a maximum contribution value) from a state candidate set as an initial state; obtaining a demonstration track taking the target state as an initial state; and updating the demonstration set, and training a strategy according to the updated demonstration set, thereby achieving the purpose of reducing the demonstration cost.

Description

technical field [0001] The embodiments of the present application relate to the communication field, and in particular, relate to an inverse reinforcement learning processing method, device, storage medium, and electronic device. Background technique [0002] Imitation learning is a way of training strategies different from reinforcement learning. By training strategies from experts' demonstrations, it can effectively reduce the duration of training. For problems with sparse reward functions, effective strategies can also be trained. Inverse reinforcement learning is a typical imitation learning method. Its idea is to learn the reward function from the demonstration of experts first, and then apply the reinforcement learning training strategy. However, the inverse reinforcement learning training strategy needs to collect a large number of expert demonstrations. In actual tasks, the cost of collecting expert demonstrations is high, and this cost is time, money, security and o...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides an inverse reinforcement learning processing method, device, storage medium, and electronic device to at least solve the problem in the related art that inverse reinforcement learning needs to collect a large number of expert demonstrations, and a large number of expert demonstrations lead to high costs.

Images