Generative confrontation interactive imitation learning method and system, storage medium and application

Abstract

The invention belongs to the technical field of artificial intelligence, and discloses a generative adversarial interactive imitation learning method and system, a storage medium and application, the generative adversarial interactive imitation learning method combines generative adversarial interactive imitation learning and an interactive learning framework to form generative adversarial interactive imitation learning GA2IL; the GA2IL is composed of two stages: (1) a GAIL-like stage based on maximum entropy inverse reinforcement learning; and (2) an interactive reinforcement learning stage. The GA2IL intelligent agent can surpass the performance of expert demonstration and obtain the optimal or near-optimal strategy under the condition that expert demonstration is optimal or suboptimal, the stability of the strategy can be improved, and the GA2IL intelligent agent can be expanded to large-scale complex tasks. According to the method, under the condition that whether optimal expert demonstration or suboptimal expert demonstration is given, the GA2IL intelligent agent can always surpass the performance of expert demonstration and can obtain an optimal strategy or a strategy close to the optimal strategy.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a method, system, storage medium and application of generative confrontation interactive imitation learning. Background technique [0002] Currently: Reinforcement Learning (RL) attempts to allow robots to learn an optimal strategy in trial-and-error learning by interacting with the real world. In recent years, with the development of deep neural networks, by combining deep learning and reinforcement learning, deep reinforcement learning (DRL) has achieved great success in many simulation tasks such as video games, sports behavior, and mechanical operations. However, due to the sparse reward signal, deep reinforcement learning, like reinforcement learning, has low sampling efficiency and slow convergence. In addition, it is very difficult to design an effective reward function for each different task. This series of problems makes it a great challeng...

AI Technical Summary

Problems solved by technology

However, recovering the weight values ​​of the reward function using a linear estimate is an ill-posed problem: different rewards can explain the same behavior

[0007] (1) Most of the existing inverse reinforcement learning algorithms need to use the model information in the inner loop, which takes a lot of running time, which limits its application in large and complex tasks; if the planning problem does not get the optimal solution, the performance of the algorithm will be greatly attenuated

Images