Application of Deep Reinforcement Learning Methods in Debt Collection

In the last few years, there is a growing interest in offline reinforcement learning (offline RL) and in reinforcement learning (RL) in general. In this paper, we presented an example of applying some of these methods to the debt collection process. We conducted several experiments using DQN, Munchausen DQN, DRQN and CQL modification for creating an optimal agent for our problem. As a result, we showed that CQL and Munchausen DQN could be successfully used in offline RL setting for debt collection process. Moreover, these agents show performance comparable with baseline DDQN agent but have several advantages for mentioned problem. We also described some practical obstacles in the usage of RL agents in a real-life task.