Alert button
Picture for Alexandra Shlychkova

Alexandra Shlychkova

Alert button

Delta Schema Network in Model-based Reinforcement Learning

Jul 08, 2020
Andrey Gorodetskiy, Alexandra Shlychkova, Aleksandr I. Panov

Figure 1 for Delta Schema Network in Model-based Reinforcement Learning
Figure 2 for Delta Schema Network in Model-based Reinforcement Learning
Figure 3 for Delta Schema Network in Model-based Reinforcement Learning

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.

* Published at the AGI 2020 conference 
Viaarxiv icon