{"total":54,"rows":[{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2107.09051","title":"AI in Finance: Challenges, Techniques and Opportunities","created":"2021-07-20","cited_by_count":81,"area":null},{"id":"2209.07089","title":"Constrained Update Projection Approach to Safe Policy Optimization","created":"2022-09-15","cited_by_count":58,"area":null},{"id":"2206.04038","title":"Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting","created":"2022-06-08","cited_by_count":54,"area":null},{"id":"2110.13716","title":"HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information","created":"2021-10-26","cited_by_count":45,"area":null},{"id":"2106.12950","title":"Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport","created":"2021-06-24","cited_by_count":32,"area":null},{"id":"2202.01511","title":"Challenging Common Assumptions in Convex Reinforcement Learning","created":"2022-02-03","cited_by_count":30,"area":"offlinerl"},{"id":"2109.13851","title":"Reinforcement Learning for Quantitative Trading","created":"2021-09-28","cited_by_count":24,"area":null},{"id":"2202.07565","title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning","created":"2022-02-15","cited_by_count":20,"area":null},{"id":"2201.09058","title":"DeepScalper: A Risk-Aware Reinforcement Learning Framework to Capture Fleeting Intraday Trading Opportunities","created":"2021-12-15","cited_by_count":15,"area":null},{"id":"2212.01209","title":"FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecasting","created":"2022-12-02","cited_by_count":15,"area":null},{"id":"2205.15434","title":"A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems","created":"2022-05-30","cited_by_count":14,"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":"2307.08873","title":"An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient","created":"2023-07-17","cited_by_count":12,"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":"2102.01985","title":"Variance Penalized On-Policy and Off-Policy Actor-Critic","created":"2021-02-03","cited_by_count":10,"area":null},{"id":"2309.00073","title":"Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction","created":"2023-08-18","cited_by_count":10,"area":"diffusion"},{"id":"2310.07747","title":"Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples","created":"2023-10-11","cited_by_count":9,"area":"offlinerl"},{"id":"2401.05430","title":"Multi-relational Graph Diffusion Neural Network with Parallel Retention for Stock Trends Classification","created":"2024-01-05","cited_by_count":9,"area":null},{"id":"2402.06656","title":"DiffsFormer: A Diffusion Transformer on Stock Factor Augmentation","created":"2024-02-05","cited_by_count":9,"area":"diffusion"},{"id":"2207.05161","title":"What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization","created":"2022-07-11","cited_by_count":5,"area":null},{"id":"2312.00344","title":"TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning","created":"2023-12-01","cited_by_count":5,"area":null},{"id":"2410.05673","title":"Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem","created":"2024-10-08","cited_by_count":5,"area":"deeprl"},{"id":"2105.03844","title":"Reinforcement Learning with Expert Trajectory For Quantitative Trading","created":"2021-05-09","cited_by_count":3,"area":null},{"id":"2107.14033","title":"Temporal-Relational Hypergraph Tri-Attention Networks for Stock Trend Prediction","created":"2021-07-22","cited_by_count":3,"area":null},{"id":"2201.05737","title":"A unified algorithm framework for mean-variance optimization in discounted Markov decision processes","created":"2022-01-15","cited_by_count":3,"area":null},{"id":"2205.10416","title":"ARLO: A Framework for Automated Reinforcement Learning","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2302.14164","title":"Stock Broad-Index Trend Patterns Learning via Domain Knowledge Informed Generative Network","created":"2023-02-27","cited_by_count":3,"area":null},{"id":"2305.04800","title":"Mlinear: Rethink the Linear Model for Time-series Forecasting","created":"2023-05-08","cited_by_count":3,"area":null},{"id":"2102.06274","title":"Hedging of Financial Derivative Contracts via Monte Carlo Tree Search","created":"2021-02-11","cited_by_count":2,"area":null},{"id":"2306.02848","title":"HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE","created":"2023-06-05","cited_by_count":2,"area":null},{"id":"2308.08135","title":"Microstructure-Empowered Stock Factor Extraction and Utilization","created":"2023-08-16","cited_by_count":2,"area":null},{"id":"2407.10775","title":"Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning","created":"2024-07-15","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":"2603.02862","title":"Learning in Markov Decision Processes with Exogenous Dynamics","created":"2026-03-03","cited_by_count":2,"area":"deeprl"},{"id":"2206.07376","title":"Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning","created":"2022-06-15","cited_by_count":1,"area":null},{"id":"2207.07578","title":"Quantitative Stock Investment by Routing Uncertainty-Aware Trading Experts: A Multi-Task Learning Approach","created":"2022-06-07","cited_by_count":1,"area":"moe"},{"id":"2210.17030","title":"Uncertainty Aware Trader-Company Method: Interpretable Stock Price Prediction Capturing Uncertainty","created":"2022-10-31","cited_by_count":1,"area":null},{"id":"2211.01762","title":"Stock Trading Volume Prediction with Dual-Process Meta-Learning","created":"2022-10-11","cited_by_count":1,"area":null},{"id":"2302.13710","title":"Global Algorithms for Mean-Variance Optimization in Markov Decision Processes","created":"2023-02-27","cited_by_count":1,"area":null},{"id":"2308.07944","title":"Portfolio Selection via Topological Data Analysis","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2406.07892","title":"A Finite-Sample Analysis of an Actor-Critic Algorithm for Mean-Variance Optimization in a Discounted MDP","created":"2024-06-12","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":"2201.09857","title":"STOPS: Short-Term-based Volatility-controlled Policy Search and its Global Convergence","created":"2022-01-24","cited_by_count":0,"area":null},{"id":"2210.15925","title":"Incorporating Interactive Facts for Stock Selection via Neural Recursive ODEs","created":"2022-10-28","cited_by_count":0,"area":null},{"id":"2212.14405","title":"Offline Policy Optimization in RL with Variance Regularizaton","created":"2022-12-29","cited_by_count":0,"area":"offlinerl"},{"id":"2307.09844","title":"Reinforcement Learning for Credit Index Option Hedging","created":"2023-07-19","cited_by_count":0,"area":null},{"id":"2402.10760","title":"RAGIC: Risk-Aware Generative Adversarial Model for Stock Interval Construction","created":"2024-02-16","cited_by_count":0,"area":null},{"id":"2410.23294","title":"Exploiting Risk-Aversion and Size-dependent fees in FX Trading with Fitted Natural Actor-Critic","created":"2024-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2504.11412","title":"Measures of Variability for Risk-averse Policy Gradient","created":"2025-04-15","cited_by_count":0,"area":"deeprl"},{"id":"2509.00793","title":"Sharpe Ratio Optimization in Markov Decision Processes","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2511.20977","title":"Independent policy gradient-based reinforcement learning for economic and reliable energy management of multi-microgrid systems","created":"2025-11-26","cited_by_count":0,"area":"deeprl"},{"id":"2602.07202","title":"Risk-Sensitive Exponential Actor Critic","created":"2026-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2609.14327","title":"Nonparametric Variance-Penalized Actor-Critic: Statistical Inference for Risk-Sensitive Reinforcement Learning","created":"2026-09-13","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}