Incontrast,our work is concerned with an overall limit on the total amount of information an agent may acquire fromtheenvironment and,inturn,howthattranslates intoitsselection ofafeasible learning target.

In this section, we provide brief background on information theory and details on our notation.

Onenaiveapproach to incorporate this ability into AI is through future trajectory prediction using model-based RL [40,19,31,54,28,26].

After that, the leaner solely and assiduously learns a target model from this dataset without further interaction.