A Multi-Agent Deep Reinforcement Learning Framework for Personalized Cancer Treatment Decision Support in Dynamic Clinical Scenarios

In the field of artificial intelligence, deep reinforcement learning (RL) has grown to be one of the most talked-about issues. It has a extensive range of applications, that may include end-to-end control, recommendation systems, robotic control and systems for natural language communication. In this paper, we have critically reviewed model-based and model-free deep reinforcement models for the treatment of cancer patients and evaluated each model based on some parameters. Based on the evaluation, a critical discussion is carried out highlighting the limitations and drawbacks of all the existing models. The analysis also gives suggestions and marks the key indicators of future needs in this domain. In the end, a solution model is proposed that tries to cover all the shortcomings and addresses the issues encountered in the existing models.