Validity Testing for Reinforcement Learning Projects

Hello,
I want to know how I can do validity testing for a reinforcement learning project. I have done my undergrad thesis on reinforcement learning using Unity ML-Agents and submitted my work in a conference. One of the reviewers are saying that validity testing needs to be done. But I do not know how I can do validity testing for RL as I did not work with any datasets. My project was, "Character Animation using Reinforcement Learning and Imitation Learning Algorithms" where I used Unity ML-Agents to train a humanoid character to walk using the RL algorithm, PPO(Proximal Policy Optimization) and IL algorithms GAIL(Generative Adversarial Imitation Learning) and BC(Behavioral Cloning).