{"list":"other","total":59,"rows":[{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"2201.05624","title":"Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next","created":"2022-01-14","cited_by_count":608},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"1711.02827","title":"Inverse Reward Design","created":"2017-11-08","cited_by_count":249},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213},{"id":"2101.06286","title":"Reinforcement learning based recommender systems: A survey","created":"2021-01-15","cited_by_count":188},{"id":"1905.10958","title":"Explainable Reinforcement Learning Through a Causal Lens","created":"2019-05-27","cited_by_count":177},{"id":"1603.01121","title":"Deep Reinforcement Learning from Self-Play in Imperfect-Information Games","created":"2016-03-03","cited_by_count":158},{"id":"2106.04895","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","created":"2021-06-09","cited_by_count":158},{"id":"2109.12843","title":"A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions","created":"2021-09-27","cited_by_count":144},{"id":"1706.10059","title":"A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem","created":"2017-06-30","cited_by_count":128},{"id":"1904.07854","title":"End-to-End Robotic Reinforcement Learning without Reward Engineering","created":"2019-04-16","cited_by_count":122},{"id":"2109.13296","title":"TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation","created":"2021-09-27","cited_by_count":120},{"id":"2004.12570","title":"The Ingredients of Real-World Robotic Reinforcement Learning","created":"2020-04-27","cited_by_count":117},{"id":"2007.13544","title":"Combining Deep Reinforcement Learning and Search for Imperfect-Information Games","created":"2020-07-27","cited_by_count":114},{"id":"1910.05396","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","created":"2019-10-11","cited_by_count":104},{"id":"1610.04286","title":"Sim-to-Real Robot Learning from Pixels with Progressive Nets","created":"2016-10-13","cited_by_count":94},{"id":"2011.09607","title":"FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance","created":"2020-11-19","cited_by_count":87},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80},{"id":"1911.10107","title":"Deep Reinforcement Learning for Trading","created":"2019-11-22","cited_by_count":73},{"id":"2111.10919","title":"Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation","created":"2021-11-21","cited_by_count":71},{"id":"2206.10558","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","created":"2022-06-21","cited_by_count":62},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62},{"id":"2007.13893","title":"Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders","created":"2020-07-27","cited_by_count":41},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40},{"id":"1909.02128","title":"No Press Diplomacy: Modeling Multi-Agent Gameplay","created":"2019-09-04","cited_by_count":38},{"id":"2207.14382","title":"Large Language Models and the Reverse Turing Test","created":"2022-07-28","cited_by_count":38},{"id":"2207.06572","title":"i-Sim2Real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loops","created":"2022-07-14","cited_by_count":32},{"id":"1904.04912","title":"Enhancing Time Series Momentum Strategies Using Deep Neural Networks","created":"2019-04-09","cited_by_count":31},{"id":"2110.02924","title":"No-Press Diplomacy from Scratch","created":"2021-10-06","cited_by_count":31},{"id":"2305.11252","title":"Brain-inspired learning in artificial neural networks: a review","created":"2023-05-18","cited_by_count":26},{"id":"1903.11774","title":"How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?","created":"2019-03-28","cited_by_count":25},{"id":"2012.03806","title":"Perspectives on Sim2Real Transfer for Robotics: A Summary of the R:SS 2020 Workshop","created":"2020-12-07","cited_by_count":25},{"id":"1901.08740","title":"Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization","created":"2019-01-25","cited_by_count":22},{"id":"1705.00109","title":"Multi-Period Trading via Convex Optimization","created":"2017-04-29","cited_by_count":21},{"id":"2109.10665","title":"A Survey on Reinforcement Learning for Recommender Systems","created":"2021-09-22","cited_by_count":18},{"id":"2203.06498","title":"The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning","created":"2022-03-12","cited_by_count":17},{"id":"2104.07246","title":"Human-in-the-Loop Deep Reinforcement Learning with Application to Autonomous Driving","created":"2021-04-15","cited_by_count":16},{"id":"2004.05940","title":"A Deep Reinforcement Learning Framework for Continuous Intraday Market Bidding","created":"2020-04-13","cited_by_count":15},{"id":"2210.11846","title":"Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities","created":"2022-10-21","cited_by_count":13},{"id":"2402.02720","title":"Discounted Adaptive Online Learning: Towards Better Regularization","created":"2024-02-05","cited_by_count":12},{"id":"1910.05471","title":"Uncertainty Quantification and Exploration for Reinforcement Learning","created":"2019-10-12","cited_by_count":11},{"id":"1904.04973","title":"Model-Free Reinforcement Learning for Financial Portfolios: A Brief Survey","created":"2019-04-10","cited_by_count":10},{"id":"2210.01774","title":"MetaTrader: An Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization","created":"2022-09-01","cited_by_count":10},{"id":"2111.05188","title":"FinRL-Podracer: High Performance and Scalable Deep Reinforcement Learning for Quantitative Finance","created":"2021-11-07","cited_by_count":9},{"id":"2210.15598","title":"Provable Sim-to-real Transfer in Continuous Domain with Partial Observations","created":"2022-10-27","cited_by_count":9},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9},{"id":"2105.00389","title":"Multi-Robot Coordination and Planning in Uncertain and Adversarial Environments","created":"2021-05-02","cited_by_count":6},{"id":"2009.03349","title":"Deep Learning and Reinforcement Learning for Autonomous Unmanned Aerial Systems: Roadmap for Theory to Deployment","created":"2020-09-07","cited_by_count":5},{"id":"2004.01504","title":"Machine Learning Algorithms for Financial Asset Price Forecasting","created":"2020-03-31","cited_by_count":3},{"id":"2212.06064","title":"Reinforcement Learning Applied to Trading Systems: A Survey","created":"2022-11-01","cited_by_count":2},{"id":"2206.05910","title":"Safe-FinRL: A Low Bias and Variance Deep Reinforcement Learning Implementation for High-Freq Stock Trading","created":"2022-06-13","cited_by_count":1},{"id":"2304.06738","title":"A Study of Biologically Plausible Neural Network: The Role and Interactions of Brain-Inspired Mechanisms in Continual Learning","created":"2023-04-13","cited_by_count":1}],"next_cursor":null}