{"total":15,"rows":[{"id":"2410.08870","title":"Can we hop in general? A discussion of benchmark selection and design using the Hopper environment","created":"2024-10-11","cited_by_count":7,"area":"deeprl"},{"id":"2402.16609","title":"Combining Transformer based Deep Reinforcement Learning with Black-Litterman Model for Portfolio Optimization","created":"2024-02-23","cited_by_count":6,"area":"deeprl"},{"id":"2407.14486","title":"Explainable Post hoc Portfolio Management Financial Policy of a Deep Reinforcement Learning agent","created":"2024-07-19","cited_by_count":3,"area":"deeprl"},{"id":"2507.00257","title":"Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning","created":"2025-06-30","cited_by_count":3,"area":"deeprl"},{"id":"2501.17992","title":"Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market Information","created":"2025-01-29","cited_by_count":2,"area":"deeprl"},{"id":"2407.16103","title":"Reinforcement Learning Pair Trading: A Dynamic Scaling approach","created":"2024-07-23","cited_by_count":1,"area":"deeprl"},{"id":"2503.04143","title":"MTS: A Deep Reinforcement Learning Portfolio Management Framework with Time-Awareness and Short-Selling","created":"2025-03-06","cited_by_count":1,"area":"deeprl"},{"id":"2501.10709","title":"Revisiting Ensemble Methods for Stock Trading and Crypto Trading Tasks at ACM ICAIF FinRL Contest 2023-2024","created":"2025-01-18","cited_by_count":0,"area":"deeprl"},{"id":"2502.07280","title":"MIGT: Memory Instance Gated Transformer Framework for Financial Portfolio Management","created":"2025-02-11","cited_by_count":0,"area":"deeprl"},{"id":"2503.22575","title":"On the Mistaken Assumption of Interchangeable Deep Reinforcement Learning Implementations","created":"2025-03-28","cited_by_count":0,"area":"deeprl"},{"id":"2505.13188","title":"When a Reinforcement Learning Agent Encounters Unknown Unknowns","created":"2025-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2605.25114","title":"Counterfactually Safe Reinforcement Learning","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2606.10412","title":"A Unified Multi-Modal Framework for Intelligent Financial Systems: Integrating Reinforcement Learning, High-Frequency Trading, and Game-Theoretic Approaches with Cross-Modal Sentiment Analysis","created":"2026-06-09","cited_by_count":0,"area":"deeprl"},{"id":"2608.15841","title":"Self-Supervised Auxiliary Task Discovery for Stable Reinforcement Learning in Stock Trading","created":"2026-08-16","cited_by_count":0,"area":"deeprl"},{"id":"2610.01325","title":"PPO-HRAP: Proximal Policy Optimization with a Hybrid Regime-Aware Policy for Risk-Controlled Trading","created":"2026-10-01","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}