The concept of imagination-augmented agents (I2A) was released in a paper titled Imagination-Augmented Agents for Deep Reinforcement Learning in February 2018 by T. Weber, et al. We have already talked about why imagination is important for learning and learning to learn. Imagination allows us to fill in the gaps in our learning and make leaps in our knowledge, if you will.
Giving agents an imagination allows us to combine model-based and model-free learning. Most of the agent algorithms we have used in this book have been model-free, meaning that we have no representative model of the environment. Early on, we did cover model-based RL with MC and DP, but most of our efforts have been fixed on model-free agents. The benefit of having a model of the environment is that the agent can then plan. Without a model, our agent just becomes reactionary...
