Imitation Game: A Model-based and Imitation Learning Deep Reinforcement Learning Hybrid

2024/04/02 by Eric MSP Veith, Torben Logemann, Veith, Eric MSP +7 · 1 voice
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #cs.AI

paper · pdf · doi:10.48550/arxiv.2404.01794

Abstract

Autonomous and learning systems based on Deep Reinforcement Learning have firmly established themselves as a foundation for approaches to creating resilient and efficient Cyber-Physical Energy Systems. However, most current approaches suffer from two distinct problems: Modern model-free algorithms such as Soft Actor Critic need a high number of samples to learn a meaningful policy, as well as a fallback to ward against concept drifts (e. g., catastrophic forgetting). In this paper, we present the work in progress towards a hybrid agent architecture that combines model-based Deep Reinforcement Learning with imitation learning to overcome both problems.

Discussions

• A Model-Based and Imitation Learning Deep Reinforcement Learning Hybrid [hn, 2 points, 0 comments]

Related

• An Introduction to Deep Reinforcement and Imitation Learning
• Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
• Energy-Based Imitation Learning
• MimicBot: Combining Imitation and Reinforcement Learning to win in Bot Bowl
• Multi-Agent Generative Adversarial Imitation Learning