Investigating Simple Object Representations in Model-Free Deep Reinforcement Learning
This addresses the challenge of enhancing cognitive capacities in reinforcement learning agents for game environments, but it appears incremental as it builds on existing methods like Rainbow.
The paper tackled the problem of improving model-free deep reinforcement learning agents by incorporating simple object representations, resulting in a substantial performance boost on the Frostbite Atari game, though no specific numbers were provided.
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. We then analyze the relative contributions of the representations of different types of objects, identify environment states where these representations are most impactful, and examine how these representations aid in generalizing to novel situations.