Reinforcement learning deep searching method based on bootstrap DAQN (deep Q network)

Abstract

The invention provides a reinforcement learning deep searching method based on bootstrap DAQN (deep Q network), mainly comprising: bootstrap DQN, deep searching and environmental background, wherein the bootstrap DQN includes a bootstrap sample and a bootstrap DQN unit; the deep searching includes deep search test and bootstrap DQN drive deep searching; the environmental background includes generating online bootstrap DQN and bootstrap DQN drive. The bootstrap DQN is a practical reinforcement learning algorithm combining deep learning and deep searching, it is proved that bootstrapping may create effective uncertain estimation on a deep neural network and may also be extended to a large-scale parallel system, information is ranked in multiple time steps, and sample diversity is guaranteed; the bootstrap DQN acts as an effective reinforcement learning algorithm in a complex environment to process mass data in parallel, calculation cost is low, learning efficiency is high, and the method has excellent performance.

Description

technical field [0001] The invention relates to the field of deep learning, in particular to a bootstrap DQN-based enhanced learning deep search method. Background technique [0002] Reinforcement learning is one of the machine learning methods. It completes the mapping learning from the environment state to the action, selects the optimal strategy according to the maximum feedback value, searches the strategy to select the optimal action, causes the state change to obtain the delayed feedback value, and evaluates the function , the iterative loop, until the learning condition is satisfied, the learning is terminated. Effective deep search is a major challenge for reinforcement learning (RL). Commonly used algorithms such as dithering algorithms require a large amount of data. However, it is difficult to obtain such a large amount of data in reality because the correct corresponding learning cannot be collected. data, making learning inefficient and computationally expensiv...

AI Technical Summary

Problems solved by technology

Effective deep search is a major challenge for reinforcement learning (RL). Commonly used algorithms such as dithering algorithms require a large amount of data. However, it is difficult to obtain such a large amount of data in reality because the correct corresponding learning cannot be collected. data, making learning inefficient and computationally expensive

Images