Delta Schema Network in Model-based Reinforcement Learning

• URL: http://arxiv.org/abs/2006.09950v2
• Date: Wed, 8 Jul 2020 05:58:54 GMT
• Title: Delta Schema Network in Model-based Reinforcement Learning
• Authors: Andrey Gorodetskiy, Alexandra Shlychkova, Aleksandr I. Panov
• Abstract summary: This work is devoted to unresolved problems of Artificial General Intelligence - the inefficiency of transfer learning. 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 Network (DSN), predicting future states of the environment and planning actions that will lead to positive reward.
• Score: 125.99533416395765
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.