Reassessing Machine Learning for Decision Analysis: Reinforcement Learning vs. Least Squares Monte Carlo for Real Option Decisions in Energy Transition

References

• Ahmadi R, Bratvold RB (2023) An exposition of least square Monte Carlo approach for real options valuation. Geoenergy Sci. Engrg. 222:111230.Crossref, Google Scholar
• Alkhatib A, Babaei M, King PR (2013) Decision making under uncertainty: Applying the least-squares Monte Carlo method in surfactant-flooding implementation. SPE J. 18(4):721–735.Crossref, Google Scholar
• Allen M, Dube O, Solecki W, Aragón-Durand F, Cramer W, Humphreys S, Kainuma M, Kala J, Mahowald N, Mulugetta Y (2018) Global warming of 1.5 °C. Report, The Intergovernmental Panel on Climate Change, Geneva.Google Scholar
• Baird L (1995) Residual algorithms: Reinforcement learning with function approximation. Prieditis A, Russell S, eds. Proc. 12th Internat. Conf. Machine Learn. (Morgan Kaufmann Publishers Inc., San Francisco), 30–37.Google Scholar
• Baxter M, Rennie A (1996) Financial Calculus: An Introduction to Derivative Pricing (Cambridge University Press, Cambridge, UK).Crossref, Google Scholar
• Bellman R (1966) Dynamic programming. Science 153(3731):34–37.Crossref, Google Scholar
• Black F, Scholes M (1973) The pricing of options and corporate liabilities. J. Political Econom. 81(3):637–654.Crossref, Google Scholar
• Boyle PP (1977) Options: A Monte Carlo approach. J. Financial Econom. 4(3):323–338.Crossref, Google Scholar
• Brandão LE, Dyer JS, Hahn WJ (2005) Using binomial decision trees to solve real-option valuation problems. Decision Anal. 2(2):69–88.Link, Google Scholar
• Bratvold R, Begg S (2010) Making Good Decisions (Society of Petroleum Engineers, Richardson, TX).Crossref, Google Scholar
• Bratvold RB, Laughton D, Enloe T, Borison A, Begg S (2005) A critical comparison of real option valuation methods: Assumptions, applicability, mechanics, and recommendations. SPE Annual Tech. Conf. Exhibition (Society of Petroleum Engineers, Richardson, TX).Google Scholar
• Broadie M, Glasserman P (1996) Estimating security price derivatives using simulation. Management Sci. 42(2):269–285.Link, Google Scholar
• Cai Y (2009) Dynamic programming and its application in economics and finance. PhD dissertation, Stanford University, Stanford, CA.Google Scholar
• Carter RG (1998) Pipeline optimization: Dynamic programming after 30 years. PSIG Annual Meeting (Pipeline Simulation Interest Group, Houston).Google Scholar
• Chi T (2000) Option to acquire or divest a joint venture. Strategic Management J. 21(6):665–687.Crossref, Google Scholar
• Chu H, Ran L, Zhang R (2016) Evaluating CCS investment of China by a novel real option‐based model. Math. Problems Engrg. 2016(1):8180674.Google Scholar
• Copeland T, Antikarov V (2001) Real Options: A Practitioner’s Guide (Texere, New York).Google Scholar
• Cox JC, Ross SA, Rubinstein M (1979) Option pricing: A simplified approach. J. Financial Econom. 7(3):229–263.Crossref, Google Scholar
• Deng Y, Bao F, Kong Y, Ren Z, Dai Q (2016) Deep direct reinforcement learning for financial signal representation and trading. IEEE Trans. Neural Networks Learn. Systems 28(3):653–664.Crossref, Google Scholar
• Dixit A (1989) Entry and exit decisions under uncertainty. J. Political Econom. 97(3):620–638.Crossref, Google Scholar
• Dixit AK, Pindyck RS (1994) Investment Under Uncertainty (Princeton University Press, Princeton, NJ).Crossref, Google Scholar
• Frayer J, Uludere NZ (2001) What is it worth? Application of real options theory to the valuation of generation assets. Electricity J. 14(8):40–51.Crossref, Google Scholar
• Gachechiladze L (2022) Real options valuation using machine learning methods. Bus. Admin. Res. Papers, No. 7, https://doi.org/10.48614/bara.7.2022.6047.Google Scholar
• Goodwin P, Wright G (2014) Decision Analysis for Management Judgment (John Wiley & Sons, Hoboken, NJ).Google Scholar
• Halperin I (2017) QLBS: Q-learner in the Black-Scholes (-Merton) worlds. Preprint, submitted December 15, https://doi.org/10.2139/ssrn.3087076.Google Scholar
• Hong A, Bratvold RB, Lake LW (2019) Fast analysis of optimal improved-oil-recovery switch time using a two-factor production model and least-squares Monte Carlo algorithm. SPE Reservoir Evaluation Engrg. 22(3):1144–1160.Crossref, Google Scholar
• Huchzermeier A, Cohen MA (1996) Valuing operational flexibility under exchange rate risk. Oper. Res. 44(1):100–113.Link, Google Scholar
• Hull JC, Basu S (2016) Options, Futures, and Other Derivatives (Pearson Education India, Chennai, India).Google Scholar
• IEA (2020) Renewables 2020. Report, International Energy Agency, Paris, https://www.iea.org/reports/renewables-2020.Google Scholar
• Iyer GC, Edmonds JA, Fawcett AA, Hultman NE, Alsalam J, Asrar GR, Calvin KV, Clarke LE, Creason J, Jeong M (2015) The contribution of Paris to limit global warming to 2 °C. Environ. Res. Lett. 10(12):125002.Crossref, Google Scholar
• Jafarizadeh B, Bratvold RB (2012) Two-factor oil-price model and real option valuation: An example of oilfield abandonment. SPE Econom. Management 4(3):158–170.Crossref, Google Scholar
• Kennedy JO (2012) Dynamic Programming: Applications to Agriculture and Natural Resources (Springer, Dordrecht, Germany).Google Scholar
• Kogut B, Kulatilaka N (2001) Capabilities as real options. Organ. Sci. 12(6):744–758.Link, Google Scholar
• Krah A-S, Nikolić Z, Korn R (2018) A least-squares Monte Carlo framework in proxy modeling of life insurance companies. Risks 6(2):62.Crossref, Google Scholar
• Kulatilaka N, Perotti EC (1998) Strategic growth options. Management Sci. 44(8):1021–1031.Link, Google Scholar
• LaValle SM (2006) Planning Algorithms (Cambridge University Press, Cambridge, UK).Crossref, Google Scholar
• Lee JS, Chun W, Roh K, Heo S, Lee JH (2023) Applying real options with reinforcement learning to assess commercial CCU deployment. J. CO2 Utilization 77:102613.Crossref, Google Scholar
• Leiblein MJ, Miller DJ (2003) An empirical examination of transaction‐ and firm‐level influences on the vertical boundaries of the firm. Strategic Management J. 24(9):839–859.Crossref, Google Scholar
• Lewis FL, Liu D (2013) Reinforcement Learning and Approximate Dynamic Programming for Feedback Control (John Wiley & Sons, Hoboken, NJ).Google Scholar
• Li N (2024) Enhancing option pricing and stock return predictions: Integrating machine learning with firm characteristics and option Greeks. Doctoral dissertation, Durham University, Durham, UK.Google Scholar
• Lint O, Pennings E (1998) R&D as an option on market introduction. R&D Management 28(4):279–287.Crossref, Google Scholar
• Longstaff FA, Schwartz ES (2001) Valuing American options by simulation: A simple least-squares approach. Rev. Financial Stud. 14(1):113–147.Crossref, Google Scholar
• Martins J, Marques RC, Cruz CO (2015) Real options in infrastructure: Revisiting the literature. J. Infrastructure Systems 21(1):04014026.Crossref, Google Scholar
• McDonald R, Siegel D (1986) The value of waiting to invest. Quart. J. Econom. 101(4):707–727.Crossref, Google Scholar
• Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529–533.Crossref, Google Scholar
• Moody J, Saffell M (2001) Learning to trade via direct reinforcement. IEEE Trans. Neural Networks 12(4):875–889.Crossref, Google Scholar
• Myers SC (1977) Determinants of corporate borrowing. J. Financial Econom. 5(2):147–175.Crossref, Google Scholar
• Myers SC (1984) Finance theory and financial strategy. Interfaces 14(1):126–137.Link, Google Scholar
• Neely JE III, De Neufville R (2001) Hybrid real options valuation of risky product development projects. Internat. J. Tech. Policy Management 1(1):29–46.Crossref, Google Scholar
• Peng C, Simon C (2024) Financial modeling with geometric Brownian motion. Open J. Bus. Management 12(2):1240–1250.Crossref, Google Scholar
• Polzin F, Migendt M, Täube FA, von Flotow P (2015) Public policy influence on renewable energy investments—A panel data study across OECD countries. Energy Policy 80:98–111.Crossref, Google Scholar
• Powell WB (2007) Approximate Dynamic Programming: Solving the Curses of Dimensionality, Wiley Series in Probability and Statistics, vol. 703 (John Wiley & Sons, Hoboken, NJ).Crossref, Google Scholar
• Puterman ML (2014) Markov Decision Processes: Discrete Stochastic Dynamic Programming (John Wiley & Sons, New York), 331–434.Google Scholar
• Puterman ML (2014) Markov Decision Processes: Discrete Stochastic Dynamic Programming (John Wiley & Sons, Hoboken, NJ).Google Scholar
• REN21 (2024) Renewables global status report. Report, REN21, Paris, https://www.ren21.net/wp-content/uploads/2019/05/GSR2024_GlobalOverview_Full_Report_with_endnotes_web.pdf.Google Scholar
• Ruf J, Wang W (2019) Neural networks for option pricing and hedging: A literature review. Preprint, submitted November 25, https://doi.org/10.2139/ssrn.3486363.Google Scholar
• Scialdone P (2007) Valuing managerial flexibility: Challenges and opportunities of the real option approach in practice. Master’s thesis, Politecnico di Milano, Milan.Google Scholar
• Sick G (1995) Real options. Jarrow RA, Maksimovic V, Ziemba WT, eds. Handbooks in Operations Research and Management Science, vol. 9 (Elsevier, Amsterdam), 631–691.Google Scholar
• Smil V (2010) Energy Transitions: History, Requirements, Prospects (Praeger, Santa Barbara, CA), 919–931.Crossref, Google Scholar
• Smith JE (2005) Alternative approaches for solving real-options problems (comment on Brandão et al. 2005). Decision Anal. 2(2):89–102.Link, Google Scholar
• Spetzler C, Winter H, Meyer J (2016) Decision Quality: Value Creation from Better Business Decisions (John Wiley & Sons, Hoboken, NJ).Crossref, Google Scholar
• Subtil Lacerda J, Van den Bergh JC (2014) International diffusion of renewable energy innovations: Lessons from the lead markets for wind power in China, Germany and USA. Energies 7(12):8236–8263.Crossref, Google Scholar
• Sutton RS, Barto AG (2018) Reinforcement Learning: An Introduction (MIT Press, Cambridge, MA).Google Scholar
• Triantis AJ (2003) Real options. Logue D, Seward J, eds. Handbook of Modern Finance (Research Institute of America, New York), D1–D32.Google Scholar
• Trigeorgis L (1993) Real options and interactions with financial flexibility. Financial Management 22(3):202–224.Crossref, Google Scholar
• Trigeorgis L (1996) Real Options: Managerial Flexibility and Strategy in Resource Allocation (MIT Press, Cambridge, MA).Google Scholar
• Trigeorgis L, Mason SP (1987) Valuing managerial flexibility. Midland Corporate Finance J. 5(1):14–21.Google Scholar
• Trigeorgis L, Reuer JJ (2017) Real options theory in strategic management. Strategic Management J. 38(1):42–63.Crossref, Google Scholar
• Willigers BJ, Begg SH, Bratvold R (2011) Valuation of swing contracts by least-squares Monte Carlo simulation. SPE Econom. Management 3(4):215–225.Crossref, Google Scholar
• Yakowitz S (1982) Dynamic programming applications in water resources. Water Resources Res. 18(4):673–696.Crossref, Google Scholar
• Zou C, Zhao Q, Zhang G, Xiong B (2016) Energy revolution: From a fossil energy era to a new energy era. Natl. Gas Indust. B 3(1):1–11.Crossref, Google Scholar