Reinforced learning algorithm based on immunologic tolerance mechanism

Abstract

The invention discloses a reinforced learning algorithm based on an immunologic tolerance mechanism. The reinforced learning algorithm based on the immunologic tolerance mechanism comprises the steps of firstly designing the vector quantity of a primary function and the vector quantity of a weight value of a TD (lambda), then encoding the vector quantity of the weight value according to the number of floating points, when the error between the environment of a system and the real environment is larger than a set threshold value, regarding the environment of the system as a primary response in an artificial immune system, when meeting the environment for the first time, optimizing the environment by the immunologic tolerance mechanism, memorizing environmental knowledge by a memory, namely an immune body, then selecting the optimal strategy according to parameters of a current system, updating the parameters of the system according to a feedback reward value (r), continuously carrying out an iteration for the next time, when the error between the environment of the system and the real environment is smaller than the threshold value, regarding the environment of the system as similar environment, regarding the similar environment as a secondary response in the artificial immune system, and directly selecting the optimal strategy according to parameters of the system through the fact that the system judges motion selection.

Description

technical field [0001] The invention relates to a reinforcement learning algorithm based on immune tolerance mechanism. Background technique [0002] Reinforcement learning is a kind of machine learning algorithm between supervised learning and unsupervised learning. It originated from behavioral psychology. It was developed in the 1980s and is currently widely used in game competitions, control systems, scheduling management, and robotics. , is a hotspot in the field of machine learning research. [0003] Reinforcement learning can learn the environment based on deterministic or non-deterministic rewards without knowing the model. Typical reinforcement learning algorithms are: Sarsa learning algorithm, Q learning algorithm, TD (λ) learning algorithm. Among them, TD(λ) learning algorithm includes tabular TD(λ) and TD(λ) based on value function approximation. In the Sarsa learning algorithm, Q learning algorithm, and tabular TD(λ), a large amount of storage space is requir...

AI Technical Summary

Problems solved by technology

Therefore, TD(λ) based on value function approximation has attracted more and more attention, but the algorithm is prone to fall into local extremum and is not convergent

Images