{"total":35,"rows":[{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203,"area":null},{"id":"2106.06135","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":66,"area":null},{"id":"2204.01855","title":"A Survey on Graph Representation Learning Methods","created":"2022-04-04","cited_by_count":66,"area":null},{"id":"2111.09395","title":"FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance","created":"2021-11-07","cited_by_count":58,"area":null},{"id":"2108.11510","title":"Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey","created":"2021-08-25","cited_by_count":43,"area":null},{"id":"2103.05115","title":"Deep reinforcement learning in medical imaging: A literature review","created":"2021-03-05","cited_by_count":34,"area":null},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2209.00532","title":"Actor Prioritized Experience Replay","created":"2022-09-01","cited_by_count":20,"area":null},{"id":"2302.10418","title":"MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization","created":"2023-02-21","cited_by_count":20,"area":null},{"id":"2208.06399","title":"AutoShard: Automated Embedding Table Sharding for Recommender Systems","created":"2022-08-12","cited_by_count":17,"area":null},{"id":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2203.10093","title":"Deep reinforcement learning guided graph neural networks for brain network analysis","created":"2022-03-18","cited_by_count":12,"area":null},{"id":"2106.05526","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","created":"2021-06-10","cited_by_count":9,"area":null},{"id":"2206.12848","title":"Analysis of Stochastic Processes through Replay Buffers","created":"2022-06-26","cited_by_count":9,"area":null},{"id":"2208.12433","title":"Towards Automated Imbalanced Learning with Deep Hierarchical Reinforcement Learning","created":"2022-08-26","cited_by_count":9,"area":null},{"id":"2304.07453","title":"Context-aware Domain Adaptation for Time Series Anomaly Detection","created":"2023-04-15","cited_by_count":8,"area":null},{"id":"2102.03261","title":"Revisiting Prioritized Experience Replay: A Value Perspective","created":"2021-02-05","cited_by_count":7,"area":null},{"id":"2110.00445","title":"Sim and Real: Better Together","created":"2021-10-01","cited_by_count":7,"area":null},{"id":"2108.04212","title":"AutoVideo: An Automated Video Action Recognition System","created":"2021-08-09","cited_by_count":6,"area":null},{"id":"2305.01868","title":"Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2211.00576","title":"Event Tables for Efficient Experience Replay","created":"2022-11-01","cited_by_count":4,"area":null},{"id":"2111.01865","title":"Off-Policy Correction for Deep Deterministic Policy Gradient Algorithms via Batch Prioritized Experience Replay","created":"2021-11-02","cited_by_count":3,"area":null},{"id":"2205.09117","title":"Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks","created":"2022-05-18","cited_by_count":3,"area":null},{"id":"2208.00755","title":"Mitigating Off-Policy Bias in Actor-Critic Methods with One-Step Q-learning: A Novel Correction Approach","created":"2022-08-01","cited_by_count":3,"area":null},{"id":"2305.14177","title":"ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2309.16743","title":"High Throughput Training of Deep Surrogates from Large Ensemble Runs","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2109.14711","title":"Explanation-Aware Experience Replay in Rule-Dense Environments","created":"2021-09-29","cited_by_count":2,"area":null},{"id":"2102.03866","title":"Model-Augmented Q-learning","created":"2021-02-07","cited_by_count":1,"area":null},{"id":"2212.12533","title":"Adaptive Risk-Aware Bidding with Budget Constraint in Display Advertising","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2302.14329","title":"Towards Personalized Preprocessing Pipeline Search","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2111.06907","title":"Improving Experience Replay through Modeling of Similar Transitions' Sets","created":"2021-11-12","cited_by_count":0,"area":null},{"id":"2210.13545","title":"MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2304.10704","title":"Interactive System-wise Anomaly Detection","created":"2023-04-21","cited_by_count":0,"area":null},{"id":"2310.01827","title":"Learning and reusing primitive behaviours to improve Hindsight Experience Replay sample efficiency","created":"2023-10-03","cited_by_count":0,"area":null},{"id":"2311.00426","title":"Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards","created":"2023-11-01","cited_by_count":0,"area":null}],"next_cursor":null}