arXiv:2607. 14373v1 Announce Type: new Abstract: We propose a noise-robust elicit-to-optimize framework that integrates inverse reinforcement learning (IRL) and reinforcement learning (RL) for eliciting agents' risk preferences and optimizing policies under a broad class of risk objectives characterized by distortion riskmetrics.
arXiv:2512.24407v2 Announce Type: replace Abstract: In many sequential decision-making problems, researchers observe actions but not the rewards that drive behavior, yet still wish to evaluate and co...
arXiv:2405.14749v3 Announce Type: replace-cross Abstract: Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL...
arXiv:2603. 09344v3 Announce Type: replace Abstract: Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift.
arXiv:2506. 07040v4 Announce Type: replace-cross Abstract: We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs).
arXiv:2607. 06610v1 Announce Type: cross Abstract: Portfolio optimization under uncertainty is inherently a multi-objective decision problem involving complex interactions among return, risk, market dynamics, and practical investment constraints.
arXiv:2608. 03562v1 Announce Type: new Abstract: Reinforcement learning (RL) with general utility extends classic RL by optimizing an arbitrary utility functional of the policy-induced occupancy measure, thereby enabling a broader range of applications.
arXiv:2609.14327v1 Announce Type: new Abstract: Variance penalization is a principled approach to risk-sensitive reinforcement learning (RL) that explicitly trades expected return for policy stabilit...
The paper introduces a statistical framework for Inverse Entropy-regularized Reinforcement Learning that resolves the non-uniqueness of reward functions by combining entropy regularization with a least-squares reconstruction of the reward from the soft Bellman residual. It models expert demonstrations as a Markov chain, estimates the expert policy via penalized maximum likelihood, and provides high-probability bounds on the excess Kullback–Leibler divergence between the estimated and true policies. These results yield non-asymptotic minimax optimal convergence rates for the least-squares reward function, highlighting the trade-offs among smoothing, model complexity, and sample size.
arXiv:2607. 09298v1 Announce Type: cross Abstract: We study general-utility Markov decision processes (GUMDPs) with risk-aware objectives.
The paper introduces Deep-BQRL, a model‑free distributional reinforcement‑learning framework that extends buffered‑quantile learning to neural function approximation. It learns conditional return quantiles from sampled transitions, constructs buffered action scores, and uses ensemble disagreement for exploration, enabling risk‑sensitive decision‑making without explicit return‑law planning. Experiments on asset‑selling and slippery FrozenLake show that Deep‑BQRL achieves smaller mean cumulative point‑quantile policy gaps than PPO and TRPO, while illustrating interpretable risk‑sensitive stopping decisions.
The paper introduces BUMEX, a reinforcement learning exploration strategy that leverages a set of prior models containing the true transition kernel and reward function. By optimizing over this model set, the method derives upper and lower bounds on the Q‑function to guide exploration, providing theoretical guarantees of convergence to the optimal policy. When the model set follows a bounded‑parameter MDP structure, the optimization becomes convex, enabling finite‑time convergence under mild assumptions and demonstrating accelerated learning in simulations.
arXiv:2602. 23672v2 Announce Type: replace-cross Abstract: This study proposes a General Bayes framework for policy learning.