{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T10:52:40Z","timestamp":1772707960277,"version":"3.50.1"},"reference-count":89,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T00:00:00Z","timestamp":1620864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>For an AI agent to make trustworthy decision recommendations under uncertainty on behalf of human principals, it should be able to explain why its recommended decisions make preferred outcomes more likely and what risks they entail. Such rationales use causal models to link potential courses of action to resulting outcome probabilities. They reflect an understanding of possible actions, preferred outcomes, the effects of action on outcome probabilities, and acceptable risks and trade-offs\u2014the standard ingredients of normative theories of decision-making under uncertainty, such as expected utility theory. Competent AI advisory systems should also notice changes that might affect a user\u2019s plans and goals. In response, they should apply both learned patterns for quick response (analogous to fast, intuitive \u201cSystem 1\u201d decision-making in human psychology) and also slower causal inference and simulation, decision optimization, and planning algorithms (analogous to deliberative \u201cSystem 2\u201d decision-making in human psychology) to decide how best to respond to changing conditions. Concepts of conditional independence, conditional probability tables (CPTs) or models, causality, heuristic search for optimal plans, uncertainty reduction, and value of information (VoI) provide a rich, principled framework for recognizing and responding to relevant changes and features of decision problems via both learned and calculated responses. This paper reviews how these and related concepts can be used to identify probabilistic causal dependencies among variables, detect changes that matter for achieving goals, represent them efficiently to support responses on multiple time scales, and evaluate and update causal models and plans in light of new data. The resulting causally explainable decisions make efficient use of available information to achieve goals in uncertain environments.<\/jats:p>","DOI":"10.3390\/e23050601","type":"journal-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T11:10:06Z","timestamp":1620904206000},"page":"601","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Information Structures for Causally Explainable Decisions"],"prefix":"10.3390","volume":"23","author":[{"suffix":"Jr.","given":"Louis","family":"Cox","sequence":"first","affiliation":[{"name":"Department of Business Analytics, University of Colorado School of Business, and MoirAI, 503 N. Franklin Street, Denver, CO 80218, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,13]]},"reference":[{"key":"ref_1","unstructured":"Wu, C.M., Schulz, E., Speekenbrink, M., Nelson, J.D., and Meder, B. (2021, April 19). Mapping the Unknown: The Spatially Correlated Multi-Armed Bandit. Available online: https:\/\/www.biorxiv.org\/content\/10.1101\/106286v2.abstract."},{"key":"ref_2","unstructured":"Heinze-Deml, C., Maathuis, M.H., and Meinshausen, N. (2021, April 19). Causal Structure Learning. Available online: https:\/\/arxiv.org\/pdf\/1706.09141.pdf."},{"key":"ref_3","unstructured":"Shu, T., Xiong, C., and Socher, R. (2021, April 19). Hierarchical and Interpretable Skill Acquisition in Multi-Task Reinforcement Learning. Available online: https:\/\/arxiv.org\/abs\/1712.07294."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Mittelstadt, B., Russell, C., and Wachter, S. (2019, January 29\u201331). Explaining Explanations in AI. Proceedings of the Conference on Fairness, Accountability, and Transparency (FAT* \u201819), New York, NY, USA.","DOI":"10.1145\/3287560.3287574"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Raiffa, H. (1968). Decision Analysis: Introductory Lectures on Choices under Uncertainty, Addison-Wesley Publishing.","DOI":"10.2307\/2987280"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Cox, L.A., Popken, D.A., and Sun, X. (2018). Causal Analytics for Applied Risk Analysis, Springer Publishing.","DOI":"10.1007\/978-3-319-78242-3"},{"key":"ref_7","unstructured":"Howard, R.A., and Matheson, J.E. (1984). Influence diagrams. The Principles and Applications of Decision Analysis, Strategic Decisions Group Publishing."},{"key":"ref_8","unstructured":"Judea, P. (2010). An introduction to causal inference. Int. J. Biostat., 6."},{"key":"ref_9","first-page":"679","article-title":"A Markovian decision process","volume":"6","author":"Bellman","year":"1957","journal-title":"J. Math. Mech."},{"key":"ref_10","unstructured":"Howard, R.A. (1960). Dynamic Programming and Markov Processes (PDF), The M.I.T. Press."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-017-08582-x","article-title":"Predicting causal relationships from biological data: Applying automated causal discovery on mass cytometry data of human immune cells","volume":"7","author":"Triantafillou","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Vineis, P., Illari, P., and Russo, F. (2017). Causality in cancer research: A journey through models in molecular epidemiology and their philosophical interpretation. Emerg. Themes Epidemiol., 14.","DOI":"10.1186\/s12982-017-0061-7"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1080\/07350015.2019.1624293","article-title":"Causal interpretations of black-box models","volume":"39","author":"Zhao","year":"2021","journal-title":"J. Bus. Econ. Stat."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1111\/j.1467-9469.2010.00722.x","article-title":"Controlled direct and mediated effects: Definition, identification and bounds","volume":"38","author":"VanderWeele","year":"2011","journal-title":"Scand. Stat. Theory Appl."},{"key":"ref_15","unstructured":"Pearl, J. (2013). Direct and indirect effects. arXiv."},{"key":"ref_16","unstructured":"John, W. (1843). A System of Logic, Parker."},{"key":"ref_17","unstructured":"Heinze-Deml, C., and Meinshausen, N. (2021, April 19). Package \u2018Compare Causal Networks\u2019. Available online: https:\/\/cran.r-project.org\/web\/packages\/CompareCausalNetworks\/CompareCausalNetworks.pdf."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Nagarajan, R., Scutari, M., and L\u00e8bre, S. (2013). Bayesian Networks in R: With Applications in Systems Biology, Springer.","DOI":"10.1007\/978-1-4614-6446-4"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wieczorek, A., and Roth, V. (2019). Information Theoretic Causal Effect Quantification. Entropy, 21.","DOI":"10.3390\/e21100975"},{"key":"ref_20","unstructured":"Wiener, N. (1956). The Theory of Prediction, McGraw-Hill."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1214\/15-AOAS806","article-title":"Inferring network structure from interventional time-course experiments","volume":"9","author":"Spencer","year":"2015","journal-title":"Ann. Appl. Stat."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lo, L.Y., Wong, M.L., Lee, K.H., and Leung, K.S. (2015). High-order dynamic Bayesian Network learning with hidden common causes for causal gene regulatory network. BMC Bioinf., 395.","DOI":"10.1186\/s12859-015-0823-6"},{"key":"ref_23","first-page":"2629","article-title":"Bayesian estimation of causal direction in acyclic structural equation models with individual-specific confounder variables and non-Gaussian distributions","volume":"15","author":"Shimizu","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/s41237-019-00095-3","article-title":"An estimation of causal structure based on Latent LiNGAM for mixed data","volume":"47","author":"Yamayoshi","year":"2020","journal-title":"Behaviormetrika"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"947","DOI":"10.1111\/rssb.12167","article-title":"Causal inference by using invariant prediction: Identification and confidence intervals","volume":"78","author":"Peters","year":"2016","journal-title":"J. R. Stat. Soc."},{"key":"ref_26","unstructured":"Heinze-Deml, C., Peters, J., and Meinshausen, N. (2021, April 19). Invariant Causal Prediction for Nonlinear Models. Available online: https:\/\/arxiv.org\/pdf\/1706.08576.pdf."},{"key":"ref_27","unstructured":"Friedman, J., Hastie, T., and Tibshirani, R. (2021, April 19). The Elements of Statistical Learning. Available online: www.web.stanford.edu\/~hastie\/ElemStatLearn."},{"key":"ref_28","first-page":"309","article-title":"Most relevant explanation in Bayesian networks","volume":"42","author":"Yuan","year":"2011","journal-title":"J. Artif. Intell. Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.jal.2016.11.028","article-title":"Hierarchical beam search for solving most relevant explanation in Bayesian networks","volume":"22","author":"Zhu","year":"2017","journal-title":"J. Appl. Logic."},{"key":"ref_30","first-page":"1887","article-title":"Robust causal inference using directed acyclic graphs: The R package \u2018dagitty\u2019","volume":"45","author":"Textor","year":"2016","journal-title":"Int. J. Epidemiol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"7345","DOI":"10.1073\/pnas.1510507113","article-title":"Causal inference and the data-fusion problem","volume":"113","author":"Bareinboim","year":"2016","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1080\/10618600.2014.907095","article-title":"Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation","volume":"24","author":"Goldstein","year":"2015","journal-title":"J. Comput. Graphical Stat."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1111\/rssb.12377","article-title":"Visualizing the effects of predictor variables in black box supervised learning models","volume":"82","author":"Apley","year":"2020","journal-title":"J. R. Stat. Soc."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1287\/opre.36.4.589","article-title":"Probabilistic inference and influence diagrams","volume":"36","author":"Shachter","year":"1988","journal-title":"Oper. Res."},{"key":"ref_35","unstructured":"Crowley, M. (2021, April 19). Evaluating Influence Diagrams. Available online: www.cs.ubc.ca\/~crowley\/papers\/aiproj.pdf."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.ijar.2015.03.007","article-title":"Equivalences between maximum a posteriori inference in Bayesian networks and maximum expected utility computation in influence diagrams","volume":"68","year":"2016","journal-title":"Int. J. Approx. Reason."},{"key":"ref_37","unstructured":"Kahneman, D. (2011). Thinking, Fast and Slow, Macmillan Publishing."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Gershman, S.J. (2017). The Oxford Handbook of Causal Reasoning, Oxford University Press. Chapter 17: Reinforcement Learning and Causal Models.","DOI":"10.1093\/oxfordhb\/9780199399550.013.20"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1249","DOI":"10.1016\/S0005-1098(00)00050-9","article-title":"A survey of computational complexity results in systems and control","volume":"36","author":"Blondel","year":"2000","journal-title":"Automatica"},{"key":"ref_40","unstructured":"Bagnell, J.A., Ng, A.Y., and Schneider, J.G. (2001). Solving Uncertain Markov Decision Processes, Carnegie Mellon University. Technical Report."},{"key":"ref_41","unstructured":"Schervish, M., Seidenfeld, T., Kadane, J., and Levi, I. (2021, April 19). Extensions of Expected Utility Theory and Some Limitations of Pairwise Comparisons. Available online: https:\/\/www.cmu.edu\/dietrich\/philosophy\/docs\/seidenfeld\/Extensions%20of%20Expected%20Utility%20and%20Pairwise%20Comparisons.pdf."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/S0004-3702(02)00378-8","article-title":"On the undecidability of probabilistic planning and related stochastic optimization problems","volume":"147","author":"Madani","year":"2003","journal-title":"Artif. Intell."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1016\/j.jcss.2016.02.009","article-title":"What is decidable about partially observable Markov decision processes with \u03c9-regular objectives","volume":"82","author":"Chatterjee","year":"2016","journal-title":"J. Comput. Syst. Sci."},{"key":"ref_44","unstructured":"Toussaint, M., Charlin, L., and Poupart, P. (2012). Hierarchical POMDP controller optimization by likelihood maximization. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Shen, W., Trevizan, F., Toyer, S., Thiebaux, S., and Xie, L. (2021, April 19). Guiding Search with Generalized Policies for Probabilistic Planning. Available online: https:\/\/shen.nz\/publication\/socs19.","DOI":"10.1609\/socs.v10i1.18507"},{"key":"ref_46","unstructured":"Parascandolo, G., Buesing, L., Merel, J., Hasenclever, L., Aslanides, J., Hamrick, J.B., Hees, N., Neitz, A., and Weber, T. (2021, April 19). Divide-and-Conquer Monte Carlo Tree Search for Goal-Directed Planning. Available online: https:\/\/arxiv.org\/pdf\/2004.11410.pdf."},{"key":"ref_47","unstructured":"Xiao, C., Huang, R., Mei, J., Schuurmans, D., and M\u00fcller, M. (2021, April 19). Maximum Entropy Monte-Carlo Planning. Available online: https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/7ffb4e0ece07869880d51662a2234143-Paper.pdf."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Eskandari, H., Mahmoodi, E., Fallah, H., and Geiger, C.D. (2011, January 11\u201314). Performance analysis of commercial simulation-based optimization packages: OptQuest and Witness optimizer. Proceedings of the 2011 Winter Simulation Conference (WSC), Phoenix, AZ, USA.","DOI":"10.1109\/WSC.2011.6147946"},{"key":"ref_49","first-page":"62","article-title":"A review of simheuristics: Extending metaheuristics to deal with stochastic combinatorial optimization problems","volume":"2","author":"Juan","year":"2015","journal-title":"Oper. Res. Perspect."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Pich\u00e9, A., Thomas, V., Ibrahim, C., Bengio, Y., and Pal, C. (2021, April 19). Probabilistic Planning with Sequential Monte Carlo Methods. Available online: https:\/\/mila.quebec\/en\/publication\/probabilistic-planning-with-sequential-monte-carlo-methods.","DOI":"10.1007\/978-981-13-2971-5_2"},{"key":"ref_51","unstructured":"Du, S., Hu, W., Li, Z., Shen, R., Song, Z., and Wu, J. (2021, April 19). When Is Particle Filtering Efficient for POMDP Sequential Planning?. Available online: https:\/\/arxiv.org\/abs\/2006.05975."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Sledge, I.J., and Pr\u00edncipe, J.C. (2018). An analysis of the value of information when exploring stochastic, discrete multi-armed bandits. Entropy, 20.","DOI":"10.3390\/e20030155"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Russo, D.J., Van Roy, B., Kazerouni, A., Osband, I., and Wen, Z. (2017). A tutorial on Thompson sampling. arXiv.","DOI":"10.1561\/9781680834710"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Kauffmann, E., Korda, N., and Munos, R. (2012). Thompson sampling: An asymptotically optimal finite time analysis. arXiv.","DOI":"10.1007\/978-3-642-34106-9_18"},{"key":"ref_55","unstructured":"Jin, C., Liu, Q., and Miryoosefi, S. (2021, April 19). Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms. Available online: https:\/\/arxiv.org\/pdf\/2102.00815.pdf."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Leike, L.T., Orseau, L., and Hutter, M. (2016). Thompson Sampling is asymptotically optimal in general environments. arXiv.","DOI":"10.24963\/ijcai.2017\/688"},{"key":"ref_57","unstructured":"Chowdhury, S.R., and Oliveira, R. (2021, April 19). No-Regret Reinforcement Learning with Value Function Approximation: A Kernel Embedding Approach. Available online: https:\/\/arxiv.org\/pdf\/2011.07881.pdf."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1287\/opre.2017.1663","article-title":"Learning to Optimize via Information-Directed Sampling","volume":"66","author":"Russo","year":"2018","journal-title":"Oper. Res."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Cheung, W.C., Simchi-Levi, D., and Zhu, R. (2019). Non-Stationary Reinforcement Learning: The Blessing of (More) Optimism. arXiv.","DOI":"10.2139\/ssrn.3397818"},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Kim, Y., Gur, Y., and Kochenderfer, M.J. (2017, January 3\u20136). Heuristics for planning with rare catastrophic events. Proceedings of the 2017 Winter Simulation Conference (WSC\u201917), Las Vegas, NV, USA.","DOI":"10.1109\/WSC.2017.8248024"},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"Moradipari, A., Alizadeh, M., and Thrampoulidis, C. (2020, January 4\u20138). Linear Thompson Sampling under unknown linear constraints. Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020), Barcelona, Spain.","DOI":"10.1109\/ICASSP40776.2020.9053865"},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Carpin, S., Chow, Y., and Pavone, M. (2016, January 16\u201321). Risk aversion in finite Markov Decision Processes using total cost criteria and average value at risk. Proceedings of the 2016 IEEE International Conference on Robotics and Automation (ICRA), Stockholm, Sweden.","DOI":"10.1109\/ICRA.2016.7487152"},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1007\/s00186-011-0367-0","article-title":"Markov decision processes with average-value-at-risk criteria","volume":"74","author":"Bauerle","year":"2011","journal-title":"Math. Meth. Oper Res."},{"key":"ref_64","doi-asserted-by":"crossref","unstructured":"Ahmadi, M., Ono, M., Ingham, M.D., Murray, R.M., and Ames, A.D. (2020, January 1\u20133). Risk-averse planning under uncertainty. Proceedings of the 2020 American Control Conference (ACC), Denver, CO, USA.","DOI":"10.23919\/ACC45564.2020.9147792"},{"key":"ref_65","unstructured":"Ahmadi, M., Rosolia, U., Ingham, M.D., Murray, R.M., and Ames, A.D. (2012). Constrained risk-averse Markov decision processes. arXiv."},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1613\/jair.5328","article-title":"DESPOT: Online POMDP planning with regularization","volume":"58","author":"Ye","year":"2017","journal-title":"J. Artif. Intell. Res."},{"key":"ref_67","first-page":"81","article-title":"Evolutionary Operation: A Method for Increasing Industrial Productivity","volume":"6","author":"Box","year":"1957","journal-title":"J. R. Stat. Soc."},{"key":"ref_68","unstructured":"Sui, Y., Gotovos, A., Burdick, J.W., and Krause, A. (2015, January 6\u201311). Safe exploration for optimization with Gaussian processes. Proceedings of the International Conference on Machine Learning (ICML), Lille, France."},{"key":"ref_69","doi-asserted-by":"crossref","unstructured":"Bai, A., Wu, F., Zhang, Z., and Chen, X. (2014, January 21\u201326). Thompson sampling based Monte-Carlo planning in POMDPs. Proceedings of the Twenty-Fourth International Conference on Automated Planning and Scheduling (ICAPS\u201914), Portsmouth, NH, USA.","DOI":"10.1609\/icaps.v24i1.13616"},{"key":"ref_70","doi-asserted-by":"crossref","unstructured":"Li, Y. (2012, January 11\u201314). Reinforcement learning algorithms for semi-Markov decision processes with average reward. Proceedings of the 9th IEEE International Conference on Networking, Sensing and Control, Beijing, China.","DOI":"10.1109\/ICNSC.2012.6204909"},{"key":"ref_71","doi-asserted-by":"crossref","first-page":"49089","DOI":"10.1109\/ACCESS.2018.2854283","article-title":"A deep hierarchical reinforcement learning algorithm in partially observable Markov decision processes","volume":"6","author":"Le","year":"2018","journal-title":"IEEE Access"},{"key":"ref_72","unstructured":"Pereira, R.d.P., and Engel, P.M. (2015). A framework for constrained and adaptive behavior-based agents. arXiv."},{"key":"ref_73","unstructured":"Kim, T., Vasilakos, T., Sakurai, K., Xiao, Y., Zhao, G., and \u015al\u0119zak, D. (2010). Automatic Skill Acquisition in Reinforcement Learning Agents Using Connection Bridge Centrality. Communication and Networking. FGCN 2010. Communications in Computer and Information Science, Springer Publishing."},{"key":"ref_74","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., and Levine, S. (2018, January 10\u201315). Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden."},{"key":"ref_75","doi-asserted-by":"crossref","unstructured":"Ortega, P.A., and Braun, D.A. (2014). Generalized Thompson sampling for sequential decision-making and causal inference. Complex Adapt. Syst. Model., 2.","DOI":"10.1186\/2194-3206-2-2"},{"key":"ref_76","unstructured":"Raj, V., and Kalyani, S. (2017). Taming non-stationary bandits: A Bayesian approach. arXiv."},{"key":"ref_77","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1137\/S0363012902402116","article-title":"Stabilizability of stochastic linear systems with finite feedback data rates","volume":"43","author":"Nair","year":"2004","journal-title":"SIAM J. Control Optim."},{"key":"ref_78","unstructured":"Achlioptas, D., Iliopoulos, F., and Vlassis, N. (2021, April 19). Stochastic Control via Entropy Compression. Available online: https:\/\/drops.dagstuhl.de\/opus\/volltexte\/2017\/7427\/pdf\/LIPIcs-ICALP-2017-83.pdf."},{"key":"ref_79","unstructured":"Tiomkin, S., Polani, D., and Tishby, N. (2017). Control capacity of partially observable dynamic systems in continuous time. arXiv."},{"key":"ref_80","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1109\/TIT.2018.2868929","article-title":"Control Capacity","volume":"65","author":"Ranade","year":"2019","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_81","unstructured":"Leike, J., and Hutter, M. (2015). On the computability of AIXI. arXiv."},{"key":"ref_82","doi-asserted-by":"crossref","first-page":"1156","DOI":"10.1103\/PhysRevLett.84.1156","article-title":"Information-theoretic limits of control","volume":"84","author":"Touchette","year":"2000","journal-title":"Phys. Rev. Lett."},{"key":"ref_83","doi-asserted-by":"crossref","unstructured":"Sinha, S., and Vaidya, U. (2017, January 4\u20136). On information transfer in discrete dynamical systems. Proceedings of the 2017 Indian Control Conference (ICC), Guwahati, India.","DOI":"10.1109\/INDIANCC.2017.7846492"},{"key":"ref_84","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","article-title":"Explanation in artificial intelligence: Insights from the social sciences","volume":"267","author":"Miller","year":"2019","journal-title":"Artif. Intell."},{"key":"ref_85","unstructured":"Ouyang, Y., Gagrani, M., Nayyar, A., and Jain, R. (2017). Learning unknown Markov Decision Processes: A Thompson sampling approach. arXiv."},{"key":"ref_86","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1287\/mnsc.34.6.679","article-title":"Decision analysis: Practice and promise","volume":"34","author":"Howard","year":"1988","journal-title":"Manag. Sci."},{"key":"ref_87","doi-asserted-by":"crossref","unstructured":"Keeney, R.L., and Raiffa, H. (1993). Decisions with Multiple Objectives: Preferences and Value Tradeoffs, John Wiley & Sons Publishing.","DOI":"10.1017\/CBO9781139174084"},{"key":"ref_88","unstructured":"Dhar, P. (2021, April 19). Understanding Causality Is the Next Challenge for Machine Learning. Available online: https:\/\/spectrum.ieee.org\/tech-talk\/artificial-intelligence\/machine-learning\/understanding-causality-is-the-next-challenge-for-machine-learning."},{"key":"ref_89","unstructured":"Sgaier, S.K., Huang, V., Summer, G.C., and The Case for Causal AI (2021, April 19). Stanford Social Innovation Review. Available online: https:\/\/ssir.org\/pdf\/Summer2020-Feature-Sgaier-Causal-AI-Updated.pdf."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/5\/601\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:00:19Z","timestamp":1760162419000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/5\/601"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,13]]},"references-count":89,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["e23050601"],"URL":"https:\/\/doi.org\/10.3390\/e23050601","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,13]]}}}