Prospect-Theory Behavior from Bellman Optimality in MDPs with Catastrophic States

• URL: http://arxiv.org/abs/2606.00970v1
• Date: Sun, 31 May 2026 03:01:48 GMT
• Title: Prospect-Theory Behavior from Bellman Optimality in MDPs with Catastrophic States
• Abstract summary: Even though rewards are linear, agent has no utility dependence, or curvature, of a catastrophe payoff at $r = 1.25$ or 13.9% at $r = 2$.<n>Across a sweep of $$ above unity has median.<n>$ above unity has median.<n>$ above unity has median.<n>$ above unity has median.<n>$ above unity has a boundary contribution exceeding.<n>the contribution in every cell.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study risk-neutral control in Markov decision processes with an absorbing catastrophic state. Even though rewards are linear and the agent has no utility curvature, probability weighting, or framing dependence, standard Bellman optimality produces three prospect-theory-like signatures: an S-shaped value-function profile (convex near catastrophe, concave in the far field), an endogenous loss-sensitivity coefficient $λ^*(S) > 1$, and a reflection-effect policy reversal. Across 495 configurations, the optimal policy plays safe near catastrophe in positive-drift (growth) regimes despite the risky action's higher immediate expected value, and plays risky near catastrophe in negative-drift (decline) regimes despite the safe action's lower immediate expected loss. We derive a closed-form expression for the asymptotic loss-aversion plateau $\barλ$ that depends only on win probability $p$, payoff asymmetry $r = |Δ_\ell/Δ_w|$, and discount factor $β$, and matches numerical solutions to $R^2 = 0.999$. The mechanism does not require asymmetric payoffs. Across a sweep of $(p,β)$ at three asymmetry levels, the asymmetry share of $\barλ$ above unity has median 4.6% at $r = 1.25$ and rises to 13.9% at $r = 2$, with the boundary contribution exceeding the asymmetry contribution in every cell tested. The phenomena persist under tabular Q-learning (a model-free agent reproduces $V^*$ at correlation 0.98 in growth and 1.00 in decline) and under stochastic transitions with Gaussian, heavy-tailed Student-$t_3$, and asymmetric skew-normal noise up to 50% of the step size, where the asymptotic plateau tracks the closed-form prediction within 0.41% for safe-channel noise and within 9.6% for risky-channel or both-channel noise. These results identify absorbing failure states as a sufficient structural mechanism for prospect-theory-like behavior under optimal control.

Related papers

• Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions [51.50375419691955]
  Distributionally robust Markov decision processes provide a principled framework for sequential decision making under model uncertainty.<n>We study how many samples are necessary and sufficient to learn an $varepsilon$-optimal robust policy under the average-reward criterion.
  arXiv  Detail & Related papers  (2026-08-06T19:49:48Z)
• The V-fold jackknife for semiparametric inference: variance estimation, confidence intervals, and simultaneous confidence bands [2.715949869811686]
  bootstrap has been a default tool for statistical inference because of its broad applicability and minimal analytic requirements.<n>We develop the $V$-fold jackknife as a computationally efficient and theoretically justified alternative for semiparametric inference.
  arXiv  Detail & Related papers  (2026-07-24T17:05:54Z)
• Sensitivity to Subjective Expected Utility Maximization: A Methodological Study, with an Illustrative Application to LLM Decision-Making [0.0]
  Vehicle is a softmax choice model with a sensitivity parameter $$ on SEU-valued alternatives.<n>The contribution is a sequence of identifiability results for $$ and for belief and utility parameters $(, )$, validated in Stansberg.<n>A two-by-two application runs end-to-end on real choice data, detecting a structured comparative $$ effect sampling in two of four cells.
  arXiv  Detail & Related papers  (2026-07-08T00:29:18Z)
• Bayesian Best-Arm Identification with Abstention: A Polynomial-to-Exponential Phase Transition [51.253617466579335]
  We study the Bayesian fixed-budget best-arm identification problem in which a learner can abstain from making a terminal recommendation.<n>We analyze the probability of undetected error--the risk of recommending a suboptimal arm without abstaining.
  arXiv  Detail & Related papers  (2026-06-28T05:07:27Z)
• How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis [53.063298916923976]
  We study the feedback in a Gaussian single-index model with $r*(x) = *(langle *, xrangle)$ and $x sim N(0, I_d)$.<n>We analyze a two-stage neural reward model that first learns the hidden direction $*$ from reward-weighted samples and then fits the readout layer by weighted ridge regression.
  arXiv  Detail & Related papers  (2026-05-23T22:00:38Z)
• Benchmarking the Utility of Privacy-Preserving Cox Regression Under Data-Driven Clipping Bounds: A Multi-Dataset Simulation Study [0.0]
  Differential privacy (DP) is a mathematical framework that guarantees individual privacy.<n>This study systematically evaluated the impact of DP mechanisms with data-driven clipping bounds on the Cox proportional hazards model.
  arXiv  Detail & Related papers  (2026-04-23T09:53:15Z)
• Artificial Intelligence and Systemic Risk: A Unified Model of Performative Prediction, Algorithmic Herding, and Cognitive Dependency in Financial Markets [0.7016842616745783]
  We develop a unified model in which AI adoption in financial markets generates systemic risk through three mutually reinforcing channels.<n>The model implies tail-loss amplification of 18--54%, economically significant relative to Basel III countercyclical buffers.
  arXiv  Detail & Related papers  (2026-03-23T06:47:55Z)
• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• A Theoretical and Empirical Taxonomy of Imbalance in Binary Classification [0.0]
  We show how imbalance shifts the discriminant boundary, yielding a deterioration slope that predicts four regimes: Normal, Mild, Extreme, and Catastrophic.<n>Across parametric and non-parametric models, empirical degradation closely follows theoretical predictions.<n>These results show that the triplet $(,,)$ provides a model-agnostic, geometrically grounded explanation of imbalance-induced deterioration.
  arXiv  Detail & Related papers  (2026-01-07T18:02:11Z)
• Understanding Robust Machine Learning for Nonparametric Regression with Heavy-Tailed Noise [10.844819221753042]
  We use Huber regression as a close-up example within Tikhonov-regularized risk minimization.<n>We address two central challenges: (i) the breakdown of standard concentration tools under weak moment assumptions, and (ii) the analytical difficulties introduced by unbounded hypothesis spaces.<n>Our study delivers principled rules, extends beyond Huber to other robust losses, and highlights prediction error, not excess risk, as the fundamental lens for analyzing robust learning.
  arXiv  Detail & Related papers  (2025-10-10T21:57:18Z)
• Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees [56.80920351680438]
  We study high-probability convergence in online learning, in the presence of heavy-tailed noise.<n>We provide guarantees for a broad class of nonlinearities, without any assumptions on noise moments.
  arXiv  Detail & Related papers  (2024-10-17T18:25:28Z)
• Autoregressive Bandits [58.46584210388307]
  We propose a novel online learning setting, Autoregressive Bandits, in which the observed reward is governed by an autoregressive process of order $k$. We show that, under mild assumptions on the reward process, the optimal policy can be conveniently computed. We then devise a new optimistic regret minimization algorithm, namely, AutoRegressive Upper Confidence Bound (AR-UCB), that suffers sublinear regret of order $widetildemathcalO left( frac(k+1)3/2sqrtnT (1-G
  arXiv  Detail & Related papers  (2022-12-12T21:37:36Z)
• Uncertainty Quantification of the 4th kind; optimal posterior accuracy-uncertainty tradeoff with the minimum enclosing ball [1.6009195333398072]
  We introduce a 4th kind of approach to Uncertainty Quantification (UQ) It can be summarized as, after observing a sample $x$, defining a likelihood region through the relative likelihood and playing a minmax game in that region to define optimal estimators and their risk. The proposed method addresses the brittleness of Bayesian inference by navigating the robustness-accuracy tradeoff associated with data assimilation.
  arXiv  Detail & Related papers  (2021-08-24T04:02:45Z)
• Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret [115.85354306623368]
  We study risk-sensitive reinforcement learning in episodic Markov decision processes with unknown transition kernels. We propose two provably efficient model-free algorithms, Risk-Sensitive Value Iteration (RSVI) and Risk-Sensitive Q-learning (RSQ) We prove that RSVI attains an $tildeObig(lambda(|beta| H2) cdot sqrtH3 S2AT big)$ regret, while RSQ attains an $tildeObig(lambda
  arXiv  Detail & Related papers  (2020-06-22T19:28:26Z)
• Provably Efficient Safe Exploration via Primal-Dual Policy Optimization [105.7510838453122]
  We study the Safe Reinforcement Learning (SRL) problem using the Constrained Markov Decision Process (CMDP) formulation. We present an provably efficient online policy optimization algorithm for CMDP with safe exploration in the function approximation setting.
  arXiv  Detail & Related papers  (2020-03-01T17:47:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.