{"list":"other","total":52,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"2011.00027","title":"The power of quantum neural networks","created":"2020-10-30","cited_by_count":379},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"2010.02174","title":"A rigorous and robust quantum speed-up in supervised machine learning","created":"2020-10-05","cited_by_count":271},{"id":"2405.10369","title":"Reinforcement learning","created":"2024-05-16","cited_by_count":247},{"id":"1811.12560","title":"An Introduction to Deep Reinforcement Learning","created":"2018-11-30","cited_by_count":206},{"id":"1907.00397","title":"Variational Quantum Circuits for Deep Reinforcement Learning","created":"2019-06-30","cited_by_count":167},{"id":"1907.02057","title":"Benchmarking Model-Based Reinforcement Learning","created":"2019-07-03","cited_by_count":162},{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143},{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139},{"id":"2405.00781","title":"Barren Plateaus in Variational Quantum Computing","created":"2024-05-01","cited_by_count":133},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111},{"id":"2103.05577","title":"Parametrized quantum policies for reinforcement learning","created":"2021-03-09","cited_by_count":90},{"id":"2403.07059","title":"Better than classical? The subtle art of benchmarking quantum machine learning models","created":"2024-03-11","cited_by_count":85},{"id":"2010.10217","title":"Quantum circuit architecture search for variational quantum algorithms","created":"2020-10-20","cited_by_count":82},{"id":"1610.08251","title":"Quantum-enhanced machine learning","created":"2016-10-26","cited_by_count":79},{"id":"2008.07524","title":"Reinforcement Learning with Quantum Variational Circuits","created":"2020-08-15","cited_by_count":77},{"id":"2103.05127","title":"Model Complexity of Deep Learning: A Survey","created":"2021-03-08","cited_by_count":65},{"id":"1806.08295","title":"How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments","created":"2018-06-21","cited_by_count":60},{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55},{"id":"2211.03464","title":"A Survey on Quantum Reinforcement Learning","created":"2022-11-07","cited_by_count":53},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49},{"id":"1611.06256","title":"Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU","created":"2016-11-18","cited_by_count":48},{"id":"2408.12739","title":"Quantum Convolutional Neural Networks are Effectively Classically Simulable","created":"2024-08-22","cited_by_count":37},{"id":"2006.16958","title":"Evaluating the Performance of Reinforcement Learning Algorithms","created":"2020-06-30","cited_by_count":36},{"id":"2112.08451","title":"Quantum Algorithms for Reinforcement Learning with a Generative Model","created":"2021-12-15","cited_by_count":24},{"id":"2206.04741","title":"Quantum Policy Iteration via Amplitude Estimation and Grover Search -- Towards Quantum Advantage for Reinforcement Learning","created":"2022-06-09","cited_by_count":21},{"id":"2212.06663","title":"Quantum Policy Gradient Algorithm with Optimized Action Decoding","created":"2022-12-13","cited_by_count":21},{"id":"1612.05695","title":"Reinforcement Learning Using Quantum Boltzmann Machines","created":"2016-12-17","cited_by_count":20},{"id":"2203.01889","title":"Quantum Reinforcement Learning via Policy Iteration","created":"2022-03-03","cited_by_count":19},{"id":"1308.4828","title":"The Sample-Complexity of General Reinforcement Learning","created":"2013-08-22","cited_by_count":18},{"id":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17},{"id":"2202.12180","title":"Quantum Deep Reinforcement Learning for Robot Navigation Tasks","created":"2022-02-24","cited_by_count":16},{"id":"2406.16241","title":"Position: Benchmarking is Limited in Reinforcement Learning Research","created":"2024-06-23","cited_by_count":15},{"id":"2305.11032","title":"Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL","created":"2023-05-18","cited_by_count":13},{"id":"2305.13681","title":"GUARD: A Safe Reinforcement Learning Benchmark","created":"2023-05-23","cited_by_count":13},{"id":"2302.10796","title":"Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret","created":"2023-02-21","cited_by_count":9},{"id":"2307.00523","title":"Disentangling Hype from Practicality: On Realistically Achieving Quantum Advantage","created":"2023-07-02","cited_by_count":8},{"id":"2404.06314","title":"Qiskit-Torch-Module: Fast Prototyping of Quantum Neural Networks","created":"2024-04-09","cited_by_count":8},{"id":"2302.08617","title":"Quantum Computing Provides Exponential Regret Improvement in Episodic Reinforcement Learning","created":"2023-02-16","cited_by_count":6},{"id":"2304.13571","title":"Quantum Natural Policy Gradients: Towards Sample-Efficient Reinforcement Learning","created":"2023-04-26","cited_by_count":6},{"id":"1706.00074","title":"Free energy-based reinforcement learning using a quantum processor","created":"2017-05-29","cited_by_count":4},{"id":"2109.10900","title":"Towards Multi-Agent Reinforcement Learning using Quantum Boltzmann Machines","created":"2021-09-22","cited_by_count":4},{"id":"2404.10017","title":"Model-based Offline Quantum Reinforcement Learning","created":"2024-04-14","cited_by_count":4},{"id":"2405.19045","title":"To RL or not to RL? An Algorithmic Cheat-Sheet for AI-Based Radio Resource Management","created":"2024-05-29","cited_by_count":2},{"id":"2209.06669","title":"Efficient Beam Search for Initial Access Using Collaborative Filtering","created":"2022-09-14","cited_by_count":1}],"next_cursor":null}