{"total":25,"rows":[{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40,"area":null},{"id":"2203.02638","title":"Safe Reinforcement Learning for Legged Locomotion","created":"2022-03-05","cited_by_count":35,"area":null},{"id":"2201.12417","title":"Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error","created":"2022-01-28","cited_by_count":32,"area":null},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2405.05349","title":"Offline Model-Based Optimization via Policy-Guided Gradient Search","created":"2024-05-08","cited_by_count":19,"area":null},{"id":"2305.04073","title":"Explaining RL Decisions with Trajectories","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2102.04285","title":"RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning Workloads","created":"2021-02-08","cited_by_count":5,"area":null},{"id":"2107.01360","title":"Supervised Off-Policy Ranking","created":"2021-07-03","cited_by_count":3,"area":null},{"id":"2206.14198","title":"Predicting the Need for Blood Transfusion in Intensive Care Units with Reinforcement Learning","created":"2022-06-26","cited_by_count":3,"area":null},{"id":"2305.00905","title":"BCQQ: Batch-Constraint Quantum Q-Learning with Cyclic Data Re-uploading","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2401.01369","title":"RL-MPCA: A Reinforcement Learning Based Multi-Phase Computation Allocation Approach for Recommender Systems","created":"2023-12-27","cited_by_count":3,"area":null},{"id":"2109.01768","title":"Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms","created":"2021-09-04","cited_by_count":2,"area":null},{"id":"2306.08044","title":"Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care","created":"2023-06-13","cited_by_count":2,"area":null},{"id":"2109.09034","title":"Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning","created":"2021-09-19","cited_by_count":1,"area":null},{"id":"2303.13489","title":"Boosting Reinforcement Learning and Planning with Demonstrations: A Survey","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2305.03870","title":"Knowledge Transfer from Teachers to Learners in Growing-Batch Reinforcement Learning","created":"2023-05-05","cited_by_count":1,"area":null},{"id":"2409.15753","title":"Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2108.12916","title":"A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning","created":"2021-08-29","cited_by_count":0,"area":null},{"id":"2202.12578","title":"Learning to Liquidate Forex: Optimal Stopping via Adaptive Top-K Regression","created":"2022-02-25","cited_by_count":0,"area":null},{"id":"2205.13950","title":"Non-Markovian policies occupancy measures","created":"2022-05-27","cited_by_count":0,"area":null},{"id":"2210.11111","title":"The Pump Scheduling Problem: A Real-World Scenario for Reinforcement Learning","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2212.08302","title":"Safe Evaluation For Offline Learning: Are We Ready To Deploy?","created":"2022-12-16","cited_by_count":0,"area":null},{"id":"2310.08660","title":"Learning RL-Policies for Joint Beamforming Without Exploration: A Batch Constrained Off-Policy Approach","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2509.03393","title":"Exploring a Graph-based Approach to Offline Reinforcement Learning for Sepsis Treatment","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2605.19457","title":"Generative Auto-Bidding with Unified Modeling and Exploration","created":"2026-05-19","cited_by_count":0,"area":null}],"next_cursor":null}