Delta Schema Network in Model-based Reinforcement Learning
This addresses transfer learning challenges in reinforcement learning for AI applications, but is incremental as it builds on existing schema networks.
The paper tackles the inefficiency of transfer learning in reinforcement learning by extending schema networks to extract logical relationships between objects and actions, resulting in strong performance on Atari games.
This work is devoted to unresolved problems of Artificial General Intelligence - the inefficiency of transfer learning. One of the mechanisms that are used to solve this problem in the area of reinforcement learning is a model-based approach. In the paper we are expanding the schema networks method which allows to extract the logical relationships between objects and actions from the environment data. We present algorithms for training a Delta Schema Network (DSN), predicting future states of the environment and planning actions that will lead to positive reward. DSN shows strong performance of transfer learning on the classic Atari game environment.