Blockchain-assisted Demonstration Cloning for Multi-Agent Deep Reinforcement Learning
This addresses sample efficiency and security issues in MDRL for users in cooperative or competitive environments, representing an incremental improvement by combining existing techniques like imitation learning with blockchain.
The paper tackles challenges in Multi-Agent Deep Reinforcement Learning (MDRL) by proposing a Blockchain-assisted Multi-Expert Demonstration Cloning (MEDC) framework, which uses expert demonstrations and a blockchain-based model sharing system to improve learning speed and resilience against faulty or malicious models, outperforming existing methods in benchmarks.
Multi-Agent Deep Reinforcement Learning (MDRL) is a promising research area in which agents learn complex behaviors in cooperative or competitive environments. However, MDRL comes with several challenges that hinder its usability, including sample efficiency, curse of dimensionality, and environment exploration. Recent works proposing Federated Reinforcement Learning (FRL) to tackle these issues suffer from problems related to model restrictions and maliciousness. Other proposals using reward shaping require considerable engineering and could lead to local optima. In this paper, we propose a novel Blockchain-assisted Multi-Expert Demonstration Cloning (MEDC) framework for MDRL. The proposed method utilizes expert demonstrations in guiding the learning of new MDRL agents, by suggesting exploration actions in the environment. A model sharing framework on Blockchain is designed to allow users to share their trained models, which can be allocated as expert models to requesting users to aid in training MDRL systems. A Consortium Blockchain is adopted to enable traceable and autonomous execution without the need for a single trusted entity. Smart Contracts are designed to manage users and models allocation, which are shared using IPFS. The proposed framework is tested on several applications, and is benchmarked against existing methods in FRL, Reward Shaping, and Imitation Learning-assisted RL. The results show the outperformance of the proposed framework in terms of learning speed and resiliency to faulty and malicious models.