Development and implementation of an intelligent assisted teaching system for Chinese English based on natural language processing and reinforcement learning

In the proposed allocation scheme, an adaptive mechanism called learning decision maker is introduced to enable the DRL agent to interact with the communication system, determine the speed of network training optimization based on the time-varying information of the communication environment, and enable the network to train more efficiently. In addition, selecting memory blocks in previous work. The simulation results show that the addition of the learning decision maker mechanism can accelerate the convergence of the neural network and achieve a higher overall system rate. Customized systems are currently mainly aimed at fields such as composition and grammar, with few translation teaching platforms, and none of them include systems for the number of passive reflective elements in IRS is set to 16, a constant interval around 80 rounds. The Critic network is updated twice are set to 0.001 and 0.002, respectively. The optimizer for D3QN and TD3 networks is the Adam optimizer, which can correct weights, biases, and learning rates during operation. This article aims to implement an English translation teaching assistance system that supports intelligent analysis.