Hybrid expert reinforcement learning method and system

Abstract

The invention provides a hybrid expert reinforcement learning method and system, which utilize a multi-head agent with shared network parameters as a plurality of experts and train the agent through adeep deterministic strategy gradient algorithm so as to learn a series of similar tasks at the same time. Each expert is introduced into an uncertainty estimate of performing an action in a state toenhance the anti-overfit Q-value assessment capability and the overall performance of the model. These enable agents to extract, migrate, and share learned knowledge (feature expressions) among different tasks, thereby improving learning efficiency of a single task and effectiveness of scheduling experts among a plurality of tasks. Different from the traditional data-driven design of a hybrid expert system, the hybrid expert system adopts a self-supervised gating network to determine an expert with the highest potential to process each interaction of an unknown task, and can completely calibrate the scheduling accuracy through uncertainty estimation fed back by the expert system under the condition of no man-made external supervision information.

Description

technical field [0001] The invention relates to the technical field of computer data processing, in particular to a mixed-expert reinforcement learning method and system. Background technique [0002] Learning related tasks in different domains and transferring the trained knowledge to new environments is a major challenge in reinforcement learning. However, most reinforcement learning methods suffer from low data utilization efficiency and slow training speed, which cannot be generalized in complex environments, which simultaneously limit their adaptability and applicability in multi-task scenarios. [0003] Mixture-of-Experts (MoE) is an effective integrated learning method that uses a gating network to make sub-models expert, thereby alleviating the problem of a single model being easy to overfit and improving complex tasks. performance; but the balance and effectiveness of expert scheduling and utilization in general hybrid expert systems are poor. Contents of the inv...

AI Technical Summary

Problems solved by technology

However, most reinforcement learning methods are inefficient in data utilization, slow in training speed, and unable to generalize in complex environments, which simultaneously limit their adaptability and applicability in multi-task scenarios

[0003] Mixture-of-Experts (MoE) is an effective ensemble learning method that uses a gating network to make sub-models expertized, thereby alleviating the problem of a single model being easy to overfit and improving complex tasks. performance; but the balance and effectiveness of expert scheduling and utilization in general hybrid expert systems are poor

Images