Preprint
Article

This version is not peer-reviewed.

Decentralized Intelligence in GameFi: Embodied AI Agents and the Convergence of DeFi and Virtual Ecosystems

Submitted:

14 January 2025

Posted:

14 January 2025

You are already at the latest version

Abstract
In the rapidly evolving landscape of GameFi, a fusion of gaming and decentralized finance (DeFi), there exists a critical need to enhance player engagement and economic interaction within gaming ecosystems. Our GameFi ecosystem aims to fundamentally transform this landscape by integrating advanced embodied AI agents into GameFi platforms. These AI agents, developed using cutting-edge large language models (LLMs), such as GPT-4 and Claude AI, are capable of proactive, adaptive, and contextually rich interactions with players. By going beyond traditional scripted responses, these agents become integral participants in the game's narrative and economic systems, directly influencing player strategies and in-game economies. We address the limitations of current GameFi platforms, which often lack immersive AI interactions and mechanisms for community engagement or creator monetization. Through the deep integration of AI agents with blockchain technology, we establish a consensus-driven, decentralized GameFi ecosystem. This ecosystem empowers creators to monetize their contributions and fosters democratic collaboration among players and creators. Furthermore, by embedding DeFi mechanisms into the gaming experience, we enhance economic participation and provide new opportunities for financial interactions within the game. Our approach enhances player immersion and retention and advances the GameFi ecosystem by bridging traditional gaming with Web3 technologies. By integrating sophisticated AI and DeFi elements, we contribute to the development of more engaging, economically robust, and community-centric gaming environments. This project represents a significant advancement in the state-of-the-art in GameFi, offering insights and methodologies that can be applied throughout the gaming industry.
Keywords: 
;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  

1. Introduction

The advent of blockchain technology has catalyzed the emer- gence of decentralized finance ( DeFi) and non-fungible to-kens (NFTs), reshaping traditional financial systems and dig- ital asset ownership (Scha¨r, 2021; Chen & Bellavitis, 2020). Within this transformative landscape, GameFi, a fusion of gaming and DeFi, has gained significant traction by introduc- ing financial mechanisms into gaming environments, allow- ing players to earn real economic value through gameplay. GameFi platforms leverage blockchain transparency and se- curity to empower players with true ownership of in-game assets, fostering play-to-earn models that have redefined user engagement and monetization strategies (Zyda, 2005).
Despite promising prospects, maintaining long-term player participation and enhancing the depth of economic interac- tions within GameFi platforms remain critical challenges. Traditional GameFi applications often lack sophisticated arti- ficial intelligence (AI) capabilities, resulting in static and pre- dictable gameplay that fails to adapt to individual player be- haviors or provide personalized experiences. This limitation not only diminishes player retention but also restricts the po- tential for dynamic in-game economies that mirror the com- plexities of real-world financial systems (Sifa, Bauckhage, & Drachen, 2014).
Simultaneously, advancements in AI, particularly in large language models (LLMs) like GPT-3 and GPT-4, have demonstrated remarkable capabilities in natural language un- derstanding and generation (Brown et al., 2020; Achiam et al., 2023). Embodied AI agents—agents capable of interact- ing within virtual or physical environments—offer new av- enues for creating immersive, responsive gaming experiences (Mott & Lester, 2006; Savva et al., 2019). These agents can learn from and adapt to user interactions, providing a level of dynamism and personalization previously unattain- able in-game environments (Bakkes, Spronck, & Van den Herik, 2009).
However, integrating advanced AI agents into decentral- ized gaming platforms presents significant technical and in- frastructure challenges. Issues such as scalability, perfor- mance bottlenecks, and maintaining decentralization princi- ples complicate the implementation of AI within blockchain- based games (Xie et al., 2019; Zheng, Xie, Dai, Chen, & Wang, 2018). Moreover, current GameFi platforms often lack mechanisms to effectively support community participa- tion and creator monetization, limiting collaborative content creation and innovation within the ecosystem (Kow & Nardi, 2010).

1.1. Problem Definition

Lack of Immersive AI Interactions in GameFi Platforms. Existing GameFi platforms predominantly feature determin- istic game mechanics and limited AI functionality, leading to repetitive gameplay experiences (Sifa et al., 2014). The ab- sence of advanced AI agents restricts the game’s ability to adapt dynamically to player actions, hindering personaliza- tion and long-term engagement. This limitation is evident in popular GameFi titles where economic incentives are pro- vided, but the gameplay lacks depth and adaptability.
Insufficient Community Engagement and Creator Mon- etization Mechanisms. While blockchain technology fa- cilitates decentralized ownership, many GameFi platforms do not fully leverage this potential to empower creators and com- munities (Xie et al., 2019). There is a significant gap in the provision of tools and systems that allow creators to con- tribute content and monetize their efforts effectively (Kow & Nardi, 2010). This deficiency limits the diversity of content and stifles community-driven innovation, which is essential for a vibrant gaming ecosystem.
Technical Challenges in Integrating Advanced AI into De- centralized Environments. Integrating AI agents into de- centralized platforms is fraught with challenges related to scalability, security, and maintaining decentralization (Zheng et al., 2018; Chen & Bellavitis, 2020). AI models, par- ticularly LLMs, require substantial computational resources, which conflict with the resource constraints inherent in blockchain networks. Ensuring that AI functionalities do not compromise the decentralized ethos of blockchain plat- forms is a complex issue that has not yet been fully addressed (Nguyen & Kim, 2018).
Underutilization of DeFi Mechanisms to Enhance Eco- nomic Participation. Although DeFi has introduced inno- vative financial instruments, their integration within gaming platforms is often superficial (Scha¨r, 2021; Chen & Bellavi- tis, 2020). GameFi applications sometimes offer token-based rewards without incorporating deeper DeFi functionality such as stakes, yield farming, or decentralized governance, limit- ing economic participation and opportunities for players and creators.

1.2. Importance of Addressing These Challenges

Enhancing Player Engagement and Retention. Address- ing the lack of immersive AI interactions is crucial to in- crease player engagement on GameFi platforms. By incorpo- rating advanced AI agents, games can offer personalized ex- periences that adapt to individual player behavior, improving satisfaction and retention rates (Bakkes et al., 2009). Stud- ies have shown that adaptive AI can significantly improve the user experience by providing appropriate challenges and in- teractions.
Fostering Community Development and Creator Empow- erment. Implementing mechanisms for community en- gagement and creator monetization can lead to a more vi- brant and innovative GameFi ecosystem. Empowering cre- ators with tools and economic incentives encourages the de- velopment of diverse content, fostering an active community that contributes to the growth of the platform (Kow & Nardi, 2010).
Advancing the Integration of AI and DeFi Technologies. By overcoming technical challenges associated with integrat- ing AI into decentralized environments, it is possible to create more sophisticated and scalable GameFi platforms. This ad- vancement not only enhances the gaming experience but also pushes the boundaries of what is possible with blockchain technology, contributing to the broader field of decentralized applications (Savva et al., 2019).
Enhancing Economic Participation Through Advanced DeFi Mechanisms. Integrating deeper DeFi functionali- ties into GameFi can unlock new economic opportunities for players and creators, leading to more robust in-game economies. Features like staking, governance tokens, and decentralized exchanges can increase user engagement and provide additional incentives for participation (Scha¨r, 2021).

1.3. Key Unique Contributions

Our project aims to address these multifaceted challenges through the following unique contributions:
Development of Advanced Embodied AI Agents. We use state-of-the-art LLMs, such as GPT-4, to develop embodied AI agents capable of sophisticated interactions (Achiam et al., 2023; Brown et al., 2020). These agents can understand and generate human-like responses, adapt to player behav- iors, and provide personalized experiences. By integrating re- inforcement learning techniques, agents continually improve from interactions within the game environment (Sutton, 2018; Silver et al., 2016).
Seamless Integration into Decentralized GameFi Ecosys- tems. Our approach involves embedding AI agents into blockchain-based gaming platforms using smart contracts and decentralized protocols (Antonopoulos, 2014; Xie et al., 2019). We ensure that AI functionalities are compati- ble with the decentralized infrastructure, maintaining secu- rity and transparency. By utilizing off-chain computation and Layer 2 scaling solutions, we address scalability issues associated with running AI models on blockchain networks (Nguyen & Kim, 2018).
Empowering Creators with Monetization Opportunities. We provide creators with tools to develop content using embodied AI agents and monetize their efforts within the GameFi ecosystem (Kow & Nardi, 2010). Our platform sup- ports the creation and trading of NFTs linked to AI-generated content, enabling creators to earn from their contributions. We implement decentralized governance models that allow creators to have a say in platform development and policies (Wright & De Filippi, 2015).
Enhancing Economic Participation Through Integrated DeFi Mechanisms. Our platform integrates advanced DeFi tools, including staking, liquidity pools, yield farming, and governance tokens (Scha¨r, 2021). AI agents assist players in navigating these financial instruments, making DeFi more accessible and engaging within the gaming context. This in- tegration fosters a robust in-game economy where players can actively participate and benefit economically.
Bridging Traditional Gaming with Web3 Technologies Using Embodied AI Agents. We aim to create a bridge between traditional gaming and Web3 technologies by inte- grating embodied AI agents into existing game environments. Our plugins allow for the addition of AI interactions and Web3 capabilities in a decentralized manner, facilitating the adoption of blockchain technologies in mainstream gaming. This approach democratizes game development and promotes collective growth within the gaming community (Batubara, Ubacht, & Janssen, 2018; Antonopoulos, 2014).

3. Approach

The integration of advanced AI agents within decentralized GameFi ecosystems presents multifaceted challenges, partic- ularly in achieving seamless interaction between blockchain infrastructure and intelligent gameplay elements. To ad- dress these challenges, our project developed a comprehen- sive GameFi application prototype that prioritizes core func- tionalities such as in-game asset management, player inter- actions, and robust blockchain integration using Alchemy’s API. The subsequent sections elucidate our methodological framework, system architecture, and the strategic advance- ments our solution offers over existing models discussed in the literature.

3.1. System Architecture

Our system architecture is meticulously designed to ensure modularity, scalability, and security, encompassing three pri- mary layers: the blockchain layer, the backend layer, and the frontend layer.
Blockchain Layer: At the foundation lies the Ethereum blockchain, selected for its maturity, extensive developer ecosystem, and robust security features. We developed a Solidity-based smart contract, GameAsset.sol, responsible for the creation, ownership, and transfer of in-game assets. This contract ensures that all asset-related transactions are immutable, transparent, and verifiable on-chain, thereby fos- tering trust among players. By utilizing Ethereum’s decen- tralized ledger, we eliminate single points of failure and pro- vide a trustless environment where asset integrity is uncom- promised.
Backend Layer: The backend, implemented using Ex- press.js, serves as the intermediary between the fron- tend interface and the blockchain. Leveraging Alchemy’s API enhances our ability to interact efficiently with the Ethereum network, offering high reliability and low latency in blockchain communications. The backend utilizes the ethers.js library to facilitate seamless interactions with the smart contract, managing critical operations such as asset cre- ation and transfer, and retrieving asset ownership data. This layer abstracts the complexities of direct blockchain interac- tions, providing a streamlined and secure conduit for frontend requests.
Frontend Layer: The user-facing component, built with React.js, delivers an intuitive and responsive interface for players. Integration with MetaMask enables secure wallet connections, allowing users to authenticate their identities and authorize transactions effortlessly. The frontend facil- itates comprehensive asset management functionalities, in- cluding creating new assets, viewing asset inventories, and transferring assets between players. Real-time updates are achieved through event listeners that respond to smart con- tract events emitted on the blockchain, ensuring that the user interface reflects the most current state of asset ownership.

3.2. Smart Contract Design

The GameAsset.sol smart contract is the cornerstone of our GameFi application, encapsulating the essential logic for as- set management within the gaming ecosystem.
  • Asset Creation: Players can mint new assets by speci- fying attributes such as name, category, and rarity. Each asset is assigned a unique identifier and linked to the player’s Ethereum address, ensuring individual owner- ship and preventing duplication.
  • Asset Transfer: Owners can transfer their assets to other players by invoking the transferAsset function. The contract enforces strict access controls, ensuring that only legitimate owners can initiate transfers, thereby safeguarding asset integrity.
  • Asset Retrieval: Through the getAssetsByOwner func- tion, players can retrieve a comprehensive list of assets they own. This facilitates easy management and over- sight of in-game assets.

3.3. Backend Integration with Alchemy’s API

Alchemy’s API plays a pivotal role in optimizing our back- end’s interaction with the Ethereum network. By provid- ing scalable and high-performance blockchain infrastructure, Alchemy ensures that our application can handle a significant volume of transactions with minimal latency.
  • Transaction Handling: The backend manages the life- cycle of transactions, from initiation to confirmation, en- suring that all blockchain interactions are executed re- liably. Utilizing ethers.js, the backend constructs and signs transactions, interacts with the smart contract func- tions, and monitors the status of transactions in real- time.
  • Event Listening: By subscribing to smart contract events (AssetCreated and AssetTransferred), the back- end can push real-time updates to the frontend. This mechanism ensures that players receive instantaneous feedback on their actions, enhancing the responsiveness and interactivity of the application.
  • Data Management: The backend efficiently handles data retrieval and storage tasks, ensuring that asset information is consistently synchronized between the blockchain and the frontend interface. This synchroniza- tion is critical for maintaining accurate and up-to-date asset inventories for all players.

3.4. Frontend Development

The frontend of our GameFi application is engineered to of- fer a seamless and engaging user experience, encompassing essential features that empower players to interact with the game environment effectively.
  • Wallet Integration: Utilizing MetaMask, players can securely connect their Ethereum wallets, facilitating au- thentication and authorization of transactions without exposing sensitive private keys.
  • User Interface: The React.js-based frontend presents a clean and intuitive dashboard where players can view their asset portfolios, create new assets, and transfer existing ones. Real-time updates ensure that all asset- related activities are immediately reflected, providing a dynamic and interactive gaming experience.
  • Transaction Feedback: Immediate visual feedback is provided for all transactions, including confirmations and error notifications. This transparency ensures that players are always informed about the status of their ac- tions, fostering trust and reliability in the application.

3.5. Integration with AI Functionalities

While the primary focus of our project was on testing GameFi components, AI functionalities are integrated using external APIs to enhance gameplay dynamics. By incorporating AI agents from the provided executable repository Embodied- AI-Agent-for-GameFi-Ecosystem, we ensure that intelligent behaviors within the game are powered by advanced machine learning models without burdening the core system architec- ture.
These AI agents interact with players, providing person- alized experiences and responsive gameplay elements that adapt to player actions in real-time. This integration under- scores the modularity of our system, where AI and blockchain components operate synergistically to deliver a rich and im- mersive GameFi ecosystem.

4. Evaluation

Our evaluation focused on assessing the GameFi application’s core functionalities, performance metrics, and security fea- tures through systematic testing methodologies.

4.1. Functional Testing

Objective: Verify the basic functionality of all system com- ponents.
Methodology:
  • Smart Contract Testing: Deployed GameAsset.sol on a local test network using Hardhat for initial testing, fol- lowed by deployment on the Goerli test network. Tested core functions including:
    Asset creation with various parameters
    Asset transfer between addresses
    Asset ownership queries
  • API Integration: Tested backend endpoints using Post- man to verify:
    Asset creation requests
    Transfer operations
    Asset retrieval functionality
  • Frontend Operations: Verified basic user interactions including:
    Wallet connection via MetaMask
    Asset creation interface
    Asset viewing and transfer capabilities
Results:
  • Contract functions executed as expected with proper event emissions
  • API endpoints handled requests appropriately
  • Frontend successfully reflected blockchain state changes

4.2. Performance Analysis

Objective: Assess basic operational efficiency.
Key Metrics:
  • Transaction confirmation times
  • Gas consumption for contract operations
Testing Approach:
  • Conducted sequential asset creation and transfer opera- tions
  • Monitored gas usage patterns
  • Analyzed transaction confirmation times
Results:
  • Transaction confirmations averaged 15-45 seconds on Goerli
  • Gas consumption:
Asset Creation: 50,000-70,000 gas units
Asset Transfer: 40,000-60,000 gas units
Query Operations: Gas-free (view functions)

4.3. Security Assessment

Objective: Validate basic security mechanisms.
Testing Methodology:
  • Access Control: Verified ownership requirements for asset transfers
  • Input Validation: Tested contract behavior with invalid inputs
  • Wallet Integration: Confirmed secure transaction sign- ing process
Results:
  • Ownership checks successfully prevented unauthorized transfers
  • Contract properly handled invalid inputs
  • MetaMask integration provided secure transaction sign- ing

4.4. Basic Load Testing

Objective: Verify system behavior under moderate usage.
Approach:
  • Simulated multiple concurrent asset operations
  • Monitored system response under various loads
Results:
  • Successfully handled multiple concurrent read opera- tions
  • Maintained consistent performance with up to 20 simul- taneous users
  • Backend remained responsive during peak testing peri- ods

5. Conclusion

The development and testing of our GameFi application pro- totype underscore the viability of integrating blockchain tech- nology with intelligent gameplay elements to create a secure, transparent and engaging gaming ecosystem. By leveraging Alchemy’s API for efficient blockchain interactions and im- plementing a robust smart contract foundation, we achieved a system that not only meets the foundational requirements of asset management and player interactions, but also sets the stage for future advancements in decentralized gaming.

High-Level Takeaways

Security and Transparency
The use of the Ethereum blockchain ensures that all transac- tions in the game and asset ownership records are immutable and transparent. This enhances player trust and reduces the risk of asset manipulation or fraud.
Performance Optimization
Strategic backend integration with Alchemy’s API and smart contract gas optimizations resulted in reduced transaction costs and maintaining acceptable confirmation times, essen- tial for a smooth gaming experience.
Scalable Architecture
The modular design of our system architecture allows for seamless scaling, enabling the application to handle increased user loads without compromising performance or stability.
User-Centric Design
An intuitive and responsive frontend interface, coupled with secure wallet integration via MetaMask, provides an accessi- ble and engaging user experience that encourages active par- ticipation and asset management.
Foundation for Advanced Features
The successful implementation of core functionalities estab- lishes a solid foundation upon which more complex game mechanics, DeFi integrations, and AI-driven features can be developed, enhancing the overall value proposition of the GameFi ecosystem.
Outstanding Questions and Areas for Future Work: While our project successfully demonstrated the integration of essential GameFi components with blockchain technology, it also opens several avenues for further research and devel- opment:
  • Advanced Gameplay Mechanics: Incorporating more complex game elements such as quests, battles, and skill progression will enhance player engagement and reten- tion. Future work could explore integrating AI-driven opponents or cooperative gameplay modes to provide a more dynamic and interactive gaming experience.
  • DeFi Integration: Expanding the application’s financial mechanisms by introducing features like staking, lend- ing, and yield farming can provide players with addi- tional ways to earn and utilize assets within the game, thereby deepening the economic interactions within the ecosystem.
  • Scalability Enhancements: Further optimization using Layer 2 solutions like Optimistic Rollups or sidechains could significantly reduce gas fees and improve trans- action speeds, making the application more viable for large-scale deployment.
  • Comprehensive Security Audits: Although prelimi- nary security testing ensured the robustness of access controls and input validations, conducting thorough se- curity audits and implementing advanced security mea- sures such as multi-signature approvals and decentral- ized identity verification will further fortify the applica- tion against potential threats.
  • Economic Modeling and Tokenomics: Developing a sustainable in-game economy with well-designed toke- nomics is crucial for long-term viability. Future research could focus on balancing asset scarcity, liquidity, and player incentives to foster a vibrant and balanced eco- nomic ecosystem.
  • AI Integration for Enhanced Interactivity: While AI functionalities were leveraged through external APIs, in- tegrating more sophisticated AI agents directly within the game infrastructure could enable personalized player experiences, adaptive challenges, and intelligent content generation, thereby enriching the overall gameplay ex- perience.
  • Cross-Blockchain Compatibility: Exploring interop- erability with other blockchain networks can broaden the application’s reach, allowing players from different ecosystems to interact and transact seamlessly. This can enhance liquidity, asset diversity, and player base, contributing to a more interconnected and expansive GameFi landscape.
Figure 1. Competitive Analysis.
Figure 1. Competitive Analysis.
Preprints 146122 g001
Figure 2. GameFi Ecosystem.
Figure 2. GameFi Ecosystem.
Preprints 146122 g002
Figure 3. Service of this GameFi Ecosysytem.
Figure 3. Service of this GameFi Ecosysytem.
Preprints 146122 g003
Figure 4. “Multi-Human-Multi AI (XHXA) Interaction Network.
Figure 4. “Multi-Human-Multi AI (XHXA) Interaction Network.
Preprints 146122 g004

Appendix A. File Repository

All executable components of this project, including the smart contract (GameAsset.sol), backend server, and frontend appli- cation, are available in our GitHub repository: https://github.com/FJDeFi/Decentralized-Intelligence-in-GameFi. This repository facilitates replication, testing, and further development of the GameFi application, providing a foundation for future research and enhancements. Comprehensive documentation is included to guide developers through the setup, deployment, and customization processes necessary to extend the application’s capabilities.
The repository hosts:
  • Smart Contracts: Solidity files with detailed comments explaining each function and its purpose.
  • Backend Server: Express.js server scripts that handle API requests and blockchain interactions.
  • Frontend Application: React.js components that deliver the user interface and manage client-side operations.
  • Deployment Scripts: Automation scripts for deploying smart contracts and initializing the backend.
  • Testing Suites: Automated tests using frameworks like Truffle and Jest to ensure functionality and performance.
  • Documentation: Step-by-step guides and API references to assist developers in understanding and utilizing the codebase effectively.

References

  1. Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., . . . others (2023). Gpt-4 technical re- port. arXiv preprint arXiv:2303.08774.
  2. Angeris, G., Kao, H.-T., Chiang, R., Noyes, C., & Chitra, T. (2021). An analysis of uniswap markets. [CrossRef]
  3. Antonopoulos, A. M. (2014). Mastering bitcoin: unlocking digital cryptocurrencies. ” O’Reilly Media, Inc.”.
  4. Bakkes, S., Spronck, P., & Van den Herik, J. (2009). Rapid and reliable adaptation of video game ai. IEEE Transactions on Computational Intelligence and AI in Games, 1(2), 93–104.
  5. Batubara, F. R., Ubacht, J., & Janssen, M. (2018). Challenges of blockchain technology adoption for e-government: a systematic literature review. In Proceedings of the 19th annual international conference on digital government research: governance in the data age (pp. 1–9).
  6. Bessembinder, H., & Venkataraman, K. (2010). Bid-ask spreads: Measuring trade execution costs in financial markets. Encyclopedia of quantitative finance, 184– 190.
  7. Biais, B., Glosten, L., & Spatt, C. (2005). Market microstruc- ture: A survey of microfoundations, empirical results, and policy implications. Journal of Financial Markets, 8(2), 217–264.
  8. Breidenbach, L., Cachin, C., Chan, B., Coventry, A., Ellis, S., Juels, A., . . . others (2021). Chainlink 2.0: Next steps in the evolution of decentralized oracle networks. Chainlink Labs, 1, 1–136.
  9. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., . . . others (2020). Language models are few-shot learners. Advances in neural information pro- cessing systems, 33, 1877–1901.
  10. Chen, Y., & Bellavitis, C. (2020). Blockchain disruption and decentralized finance: The rise of decentralized busi- ness models. Journal of Business Venturing Insights, 13, e00151.
  11. Egorov, M. (2019). Stableswap-efficient mechanism for sta- blecoin liquidity. Retrieved Feb, 24, 2021.
  12. Kow, Y. M., & Nardi, B. (2010). Culture and creativity: World of warcraft modding in china and the us. Online worlds: Convergence of the real and the virtual, 21– 41.
  13. Mott, B. W., & Lester, J. C. (2006). Narrative-centered tuto- rial planning for inquiry-based learning environments. In International conference on intelligent tutoring sys- tems (pp. 675–684).
  14. Nguyen, G.-T., & Kim, K. (2018). A survey about consensus algorithms used in blockchain. Journal of Information processing systems, 14(1).
  15. Qin, K., Zhou, L., Gamito, P., Jovanovic, P., & Gervais, A. (2021). An empirical study of defi liquidations: Incen- tives, risks, and instabilities. In Proceedings of the 21st acm internet measurement conference (pp. 336–350).
  16. Qin, K., Zhou, L., Livshits, B., & Gervais, A. (2021). At- tacking the defi ecosystem with flash loans for fun and profit. In International conference on financial cryp- tography and data security (pp. 3–32).
  17. Savva, M., Kadian, A., Maksymets, O., Zhao, Y., Wijmans, E., Jain, B., . . . others (2019). Habitat: A platform for embodied ai research. In Proceedings of the ieee/cvf in- ternational conference on computer vision (pp. 9339– 9347).
  18. Scha¨r, F. (2021). Decentralized finance: On blockchain- and smart contract-based financial markets. FRB of St. Louis Review.
  19. Sifa, R., Bauckhage, C., & Drachen, A. (2014). Archetypal game recommender systems. In Lwa (Vol. 5, pp. 45– 56).
  20. Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., . . . others (2016). Master- ing the game of go with deep neural networks and tree search. nature, 529(7587), 484–489.
  21. Sutton, R. S. (2018). Reinforcement learning: An introduc- tion. A Bradford Book.
  22. Wright, A., & De Filippi, P. (2015). Decentralized blockchain technology and the rise of lex cryptographia. Available at SSRN 2580664.
  23. Xie, J., Tang, H., Huang, T., Yu, F. R., Xie, R., Liu, J., & Liu, Y. (2019). A survey of blockchain technol- ogy applied to smart cities: Research issues and chal- lenges. IEEE communications surveys & tutorials, 21(3), 2794–2830.
  24. Zhang, F., Maram, D., Malvai, H., Goldfeder, S., & Juels, A. (2020). Deco: Liberating web data using decentralized oracles for tls. In Proceedings of the 2020 acm sigsac conference on computer and communications security (pp. 1919–1938).
  25. Zheng, Z., Xie, S., Dai, H.-N., Chen, X., & Wang, H. (2018). Blockchain challenges and opportunities: A survey. In- ternational journal of web and grid services, 14(4), 352–375.
  26. Zyda, M. (2005). From visual simulation to virtual reality to games. Computer, 38(9), 25–32. [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.