Investigating Simple Object Representations in Model-Free Deep Reinforcement Learning

Understand

We explore the benefits of augmenting state-of-the-art model-free deep reinforcement algorithms with simple object representations.

• Following the Frostbite challenge posited by Lake et al.
• (2017), we identify object representations as a critical cognitive capacity lacking from current reinforcement learning agents.
• We discover that providing the Rainbow model (Hessel et al.,2018) with simple, feature-engineered object representations substantially boosts its performance on the Frostbite game from Atari 2600.