Blockchain-based Crowdsourced Deep Reinforcement Learning as a Service

TL;DR

This paper introduces a blockchain-based crowdsourced framework that makes Deep Reinforcement Learning more accessible by enabling training and sharing of models through a secure, decentralized platform.

Contribution

It proposes a novel DRL as a Service framework leveraging blockchain and crowdsourcing, facilitating training and sharing of DRL models with incentives and traceability.

Findings

Framework successfully enables crowdsourced DRL training.

Model sharing via incentives improves access to pre-trained models.

System proves effective on multiple DRL applications.

Abstract

Deep Reinforcement Learning (DRL) has emerged as a powerful paradigm for solving complex problems. However, its full potential remains inaccessible to a broader audience due to its complexity, which requires expertise in training and designing DRL solutions, high computational capabilities, and sometimes access to pre-trained models. This necessitates the need for hassle-free services that increase the availability of DRL solutions to a variety of users. To enhance the accessibility to DRL services, this paper proposes a novel blockchain-based crowdsourced DRL as a Service (DRLaaS) framework. The framework provides DRL-related services to users, covering two types of tasks: DRL training and model sharing. Through crowdsourcing, users could benefit from the expertise and computational capabilities of workers to train DRL solutions. Model sharing could help users gain access to pre-trained models, shared by workers in return for incentives, which can help train new DRL solutions using methods in knowledge transfer. The DRLaaS framework is built on top of a Consortium Blockchain to enable traceable and autonomous execution. Smart Contracts are designed to manage worker and model allocation, which are stored using the InterPlanetary File System (IPFS) to ensure tamper-proof data distribution. The framework is tested on several DRL applications, proving its efficacy.