Modularization Of End-to-end Learning: Case Study In Arcade Games

Abstract

Complex environments and tasks pose a difficult problem for holistic end-to-end learning approaches. Decomposition of an environment into interacting controllable and non-controllable objects allows supervised learning for non-controllable objects and universal value function approximator learning for controllable objects. Such decomposition should lead to a shorter learning time and better generalisation capability. Here, we consider arcade-game environments as sets of interacting objects (controllable, non-controllable) and propose a set of functional modules that are specialized on mastering different types of interactions in a broad range of environments. The modules utilize regression, supervised learning, and reinforcement learning algorithms. Results of this case study in different Atari games suggest that human-level performance can be achieved by a learning agent within a human amount of game experience (10-15 minutes game time) when a proper decomposition of an environment or

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymelnik2019modularization

Related papers

• Modular Continual Learning In A Unified Visual Environment (2017)0.00
• Modular Object-oriented Games: A Task Framework For Reinforcement Learning, Psychology, And Neuroscience (2021)0.00
• Modularity Benefits Reinforcement Learning Agents With Competing Homeostatic Drives (2022)0.00
• Functions That Emerge Through End-to-end Reinforcement Learning - The Direction For Artificial General Intelligence - (2017)0.00
• Open-ended Learning Leads To Generally Capable Agents (2021)0.00
• Learning From Learners: Adapting Reinforcement Learning Agents To Be Competitive In A Card Game (2020)0.00
• Heterogeneous Knowledge For Augmented Modular Reinforcement Learning (2023)0.00
• An Approach To Partial Observability In Games: Learning To Both Act And Observe (2021)3.58