{"total":130,"rows":[{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2102.05371","title":"Risk-Averse Offline Reinforcement Learning","created":"2021-02-10","cited_by_count":65,"area":"offlinerl"},{"id":"2202.01288","title":"Imitation Learning by Estimating Expertise of Demonstrators","created":"2022-02-02","cited_by_count":50,"area":"offlinerl"},{"id":"2111.03947","title":"Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning","created":"2021-11-06","cited_by_count":43,"area":null},{"id":"2110.02758","title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL","created":"2021-10-06","cited_by_count":36,"area":null},{"id":"2305.16217","title":"Beyond Reward: Offline Preference-guided Policy Optimization","created":"2023-05-25","cited_by_count":35,"area":"alignment"},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2204.07417","title":"Safe Reinforcement Learning Using Black-Box Reachability Analysis","created":"2022-04-15","cited_by_count":26,"area":null},{"id":"2207.10295","title":"Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning","created":"2022-07-21","cited_by_count":22,"area":"offlinerl"},{"id":"2101.07107","title":"Deep Reinforcement Learning for Active High Frequency Trading","created":"2021-01-18","cited_by_count":21,"area":null},{"id":"2112.13414","title":"Reinforcement Learning with Dynamic Convex Risk Measures","created":"2021-12-26","cited_by_count":21,"area":null},{"id":"2108.10403","title":"Robust Risk-Aware Reinforcement Learning","created":"2021-08-23","cited_by_count":18,"area":null},{"id":"2306.11626","title":"Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity","created":"2023-06-20","cited_by_count":17,"area":null},{"id":"2203.03684","title":"Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets","created":"2022-03-07","cited_by_count":16,"area":null},{"id":"2210.14051","title":"Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds","created":"2022-10-25","cited_by_count":16,"area":null},{"id":"2102.11075","title":"SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning","created":"2021-02-22","cited_by_count":15,"area":null},{"id":"2301.12601","title":"Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents","created":"2023-01-30","cited_by_count":15,"area":null},{"id":"2106.06044","title":"Convergence and Alignment of Gradient Descent with Random Backpropagation Weights","created":"2021-06-10","cited_by_count":14,"area":null},{"id":"2407.10583","title":"Three Dogmas of Reinforcement Learning","created":"2024-07-15","cited_by_count":14,"area":"deeprl"},{"id":"2509.24261","title":"Risk-Sensitive RL for Alleviating Exploration Dilemmas in Large Language Models","created":"2025-09-29","cited_by_count":14,"area":"lr"},{"id":"2305.09793","title":"Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions","created":"2023-05-16","cited_by_count":13,"area":null},{"id":"2105.14125","title":"Joint Optimization of Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2105.14127","title":"Risk-Aware Transfer in Reinforcement Learning using Successor Features","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2109.08947","title":"Risk-averse autonomous systems: A brief history and recent developments from the perspective of optimal control","created":"2021-09-18","cited_by_count":12,"area":null},{"id":"2205.12184","title":"Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2210.01368","title":"RAP: Risk-Aware Prediction for Robust Planning","created":"2022-10-04","cited_by_count":12,"area":null},{"id":"2301.12593","title":"Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning","created":"2023-01-30","cited_by_count":12,"area":null},{"id":"2106.06499","title":"Policy Gradient Bayesian Robust Optimization for Imitation Learning","created":"2021-06-11","cited_by_count":11,"area":"offlinerl"},{"id":"2111.00411","title":"Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees","created":"2021-10-31","cited_by_count":11,"area":null},{"id":"2310.20266","title":"Beyond Average Return in Markov Decision Processes","created":"2023-10-31","cited_by_count":11,"area":null},{"id":"2408.10932","title":"The Evolution of Reinforcement Learning in Quantitative Finance: A Survey","created":"2024-08-20","cited_by_count":11,"area":"deeprl"},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2102.01985","title":"Variance Penalized On-Policy and Off-Policy Actor-Critic","created":"2021-02-03","cited_by_count":10,"area":null},{"id":"2206.14666","title":"Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning","created":"2022-06-29","cited_by_count":9,"area":null},{"id":"2406.17863","title":"What type of inference is planning?","created":"2024-06-25","cited_by_count":9,"area":null},{"id":"2410.23569","title":"RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning","created":"2024-10-31","cited_by_count":9,"area":"alignment"},{"id":"2111.02907","title":"Model-Free Risk-Sensitive Reinforcement Learning","created":"2021-11-04","cited_by_count":7,"area":null},{"id":"2309.06375","title":"Modeling Recommender Ecosystems: Research Challenges at the Intersection of Mechanism Design, Reinforcement Learning and Generative Models","created":"2023-09-08","cited_by_count":7,"area":null},{"id":"2311.13589","title":"Risk-sensitive Markov Decision Process and Learning under General Utility Functions","created":"2023-11-22","cited_by_count":7,"area":null},{"id":"2412.08794","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","created":"2024-12-11","cited_by_count":7,"area":"offlinerl"},{"id":"2104.01040","title":"Distributional Offline Continuous-Time Reinforcement Learning with Neural Physics-Informed PDEs (SciPhy RL for DOCTR-L)","created":"2021-04-02","cited_by_count":6,"area":null},{"id":"2107.04422","title":"Policy Gradient Methods for Distortion Risk Measures","created":"2021-07-09","cited_by_count":6,"area":null},{"id":"2212.14743","title":"Risk-Sensitive Policy with Distributional Reinforcement Learning","created":"2022-12-30","cited_by_count":6,"area":null},{"id":"2301.05664","title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning","created":"2023-01-13","cited_by_count":6,"area":"offlinerl"},{"id":"2302.08669","title":"Learning to Forecast Aleatoric and Epistemic Uncertainties over Long Horizon Trajectories","created":"2023-02-17","cited_by_count":6,"area":"wm"},{"id":"2305.07487","title":"Identify, Estimate and Bound the Uncertainty of Reinforcement Learning for Autonomous Driving","created":"2023-05-12","cited_by_count":6,"area":"driving"},{"id":"2403.08955","title":"Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis","created":"2024-03-13","cited_by_count":6,"area":"deeprl"},{"id":"2407.07631","title":"Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning","created":"2024-07-10","cited_by_count":6,"area":"offlinerl"},{"id":"2410.24128","title":"Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis","created":"2024-10-31","cited_by_count":6,"area":"deeprl"},{"id":"2102.00966","title":"Risk Aware and Multi-Objective Decision Making with Distributional Monte Carlo Tree Search","created":"2021-02-01","cited_by_count":5,"area":null},{"id":"2203.10045","title":"Risk-Sensitive Bayesian Games for Multi-Agent Reinforcement Learning under Policy Uncertainty","created":"2022-03-18","cited_by_count":5,"area":null},{"id":"2211.11027","title":"Safe Reinforcement Learning using Data-Driven Predictive Control","created":"2022-11-20","cited_by_count":5,"area":null},{"id":"2211.13032","title":"Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2506.00286","title":"Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model","created":"2025-05-30","cited_by_count":5,"area":"deeprl"},{"id":"2104.04036","title":"Optimal Market Making by Reinforcement Learning","created":"2021-04-08","cited_by_count":4,"area":null},{"id":"2402.15197","title":"Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization","created":"2024-02-23","cited_by_count":4,"area":"deeprl"},{"id":"2406.14156","title":"Tractable Equilibrium Computation in Markov Games through Risk Aversion","created":"2024-06-20","cited_by_count":4,"area":"deeprl"},{"id":"2107.08083","title":"Robust Risk-Sensitive Reinforcement Learning Agents for Trading Markets","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2109.04001","title":"Deep Reinforcement Learning for Equal Risk Pricing and Hedging under Dynamic Expectile Risk Measures","created":"2021-09-09","cited_by_count":3,"area":null},{"id":"2204.09833","title":"Sample-Based Bounds for Coherent Risk Measures: Applications to Policy Synthesis and Verification","created":"2022-04-21","cited_by_count":3,"area":null},{"id":"2207.13730","title":"Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control","created":"2022-07-27","cited_by_count":3,"area":null},{"id":"2209.09648","title":"Safe Reinforcement Learning with Contrastive Risk Prediction","created":"2022-09-10","cited_by_count":3,"area":null},{"id":"2309.05582","title":"Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning","created":"2023-09-11","cited_by_count":3,"area":null},{"id":"2407.18422","title":"A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2408.07962","title":"Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuning","created":"2024-08-15","cited_by_count":3,"area":"deeprl"},{"id":"2411.01827","title":"Risk-sensitive control as inference with R\\'enyi divergence","created":"2024-11-04","cited_by_count":3,"area":"deeprl"},{"id":"2606.14801","title":"QPILOTS: Efficient Test-Time Q-Steering for Flow Policies","created":"2026-06-11","cited_by_count":3,"area":"diffusion"},{"id":"2102.12585","title":"Towards Safe Continuing Task Reinforcement Learning","created":"2021-02-24","cited_by_count":2,"area":null},{"id":"2104.00075","title":"Ultra-Reliable Indoor Millimeter Wave Communications using Multiple Artificial Intelligence-Powered Intelligent Surfaces","created":"2021-03-31","cited_by_count":2,"area":null},{"id":"2104.00540","title":"Reinforcement Learning Beyond Expectation","created":"2021-03-29","cited_by_count":2,"area":null},{"id":"2203.03110","title":"Cascaded Gaps: Towards Gap-Dependent Regret for Risk-Sensitive Reinforcement Learning","created":"2022-03-07","cited_by_count":2,"area":null},{"id":"2208.03066","title":"Tailoring to the Tails: Risk Measures for Fine-Grained Tail Sensitivity","created":"2022-08-05","cited_by_count":2,"area":null},{"id":"2210.08569","title":"Limited or Biased: Modeling Sub-Rational Human Investors in Financial Markets","created":"2022-10-16","cited_by_count":2,"area":null},{"id":"2405.01718","title":"Robust Risk-Sensitive Reinforcement Learning with Conditional Value-at-Risk","created":"2024-05-02","cited_by_count":2,"area":"deeprl"},{"id":"2503.17629","title":"Planning and Learning in Average Risk-aware MDPs","created":"2025-03-22","cited_by_count":2,"area":"deeprl"},{"id":"2510.20199","title":"Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents","created":"2025-10-23","cited_by_count":2,"area":"deeprl"},{"id":"2602.00948","title":"FinEvo: From Isolated Backtests to Ecological Market Games for Multi-Agent Financial Strategy Evolution","created":"2026-02-01","cited_by_count":2,"area":"agents"},{"id":"2602.20132","title":"LAD: Learning Advantage Distribution for Reasoning","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2605.07857","title":"Actor-Critic Algorithm for Dynamic Expectile and CVaR","created":"2026-05-08","cited_by_count":2,"area":"deeprl"},{"id":"2112.03232","title":"A Risk-Averse Preview-based $Q$-Learning Algorithm: Application to Highway Driving of Autonomous Vehicles","created":"2021-12-06","cited_by_count":1,"area":"driving"},{"id":"2203.10165","title":"Privacy-Preserving Reinforcement Learning Beyond Expectation","created":"2022-03-18","cited_by_count":1,"area":null},{"id":"2208.12777","title":"Prospect Theory-inspired Automated P2P Energy Trading with Q-learning-based Dynamic Pricing","created":"2022-08-26","cited_by_count":1,"area":null},{"id":"2209.15618","title":"Beyond Bayes-optimality: meta-learning what you know you don't know","created":"2022-09-30","cited_by_count":1,"area":null},{"id":"2302.08001","title":"Learning Density-Based Correlated Equilibria for Markov Games","created":"2023-02-16","cited_by_count":1,"area":null},{"id":"2303.01768","title":"Toward Risk-based Optimistic Exploration for Cooperative Multi-Agent Reinforcement Learning","created":"2023-03-03","cited_by_count":1,"area":null},{"id":"2305.00576","title":"Joint Learning of Policy with Unknown Temporal Constraints for Safe Reinforcement Learning","created":"2023-04-30","cited_by_count":1,"area":null},{"id":"2309.11907","title":"Learning to Recover for Safe Reinforcement Learning","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2311.04946","title":"Causal Inference on Investment Constraints and Non-stationarity in Dynamic Portfolio Optimization through Reinforcement Learning","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2312.05231","title":"Modeling Risk in Reinforcement Learning: A Literature Mapping","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2407.19860","title":"Anomalous State Sequence Modeling to Enhance Safety in Reinforcement Learning","created":"2024-07-29","cited_by_count":1,"area":"deeprl"},{"id":"2408.08812","title":"TRAM: Test-Time Risk Adaptation with Mixture of Agents","created":"2024-08-16","cited_by_count":1,"area":"agents"},{"id":"2412.21004","title":"Weber-Fechner Law in Temporal Difference learning derived from Control as Inference","created":"2024-12-30","cited_by_count":1,"area":"deeprl"},{"id":"2603.10895","title":"Ergodicity in reinforcement learning","created":"2026-03-11","cited_by_count":1,"area":"deeprl"},{"id":"2605.08053","title":"Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs","created":"2026-05-08","cited_by_count":1,"area":"deeprl"},{"id":"2605.19674","title":"Beyond Rational Illusion: Behaviorally Realistic Strategic Classification","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.21763","title":"On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"id":"2606.27766","title":"RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance","created":"2026-06-26","cited_by_count":1,"area":"offlinerl"},{"id":"2607.13175","title":"SteinGate: Tail-Sensitive Safe Reinforcement Learning via Stein Discrepancy","created":"2026-07-14","cited_by_count":1,"area":"deeprl"},{"id":"2609.08064","title":"Risk-Conditioned Fine-Tuning of Large Language Models","created":"2026-09-08","cited_by_count":1,"area":null}],"next_cursor":"100"}