{"list":"other","total":94,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"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":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","cited_by_count":366},{"id":"2110.01548","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","created":"2021-10-04","cited_by_count":302},{"id":"1903.08792","title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","created":"2019-03-21","cited_by_count":289},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"1906.05433","title":"Tackling Climate Change with Machine Learning","created":"2019-06-10","cited_by_count":265},{"id":"2103.09568","title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","created":"2021-03-17","cited_by_count":256},{"id":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231},{"id":"1811.12560","title":"An Introduction to Deep Reinforcement Learning","created":"2018-11-30","cited_by_count":206},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166},{"id":"2202.09481","title":"TransDreamer: Reinforcement Learning with Transformer World Models","created":"2022-02-19","cited_by_count":143},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111},{"id":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91},{"id":"1810.08700","title":"Safe Reinforcement Learning with Model Uncertainty Estimates","created":"2018-10-19","cited_by_count":72},{"id":"1704.02254","title":"Recurrent Environment Simulators","created":"2017-04-07","cited_by_count":68},{"id":"2202.07789","title":"Safe Reinforcement Learning by Imagining the Near Future","created":"2022-02-15","cited_by_count":67},{"id":"2303.01859","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","created":"2023-03-03","cited_by_count":62},{"id":"2103.03104","title":"Learning to run a Power Network Challenge: a Retrospective Analysis","created":"2021-03-02","cited_by_count":55},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42},{"id":"1912.04211","title":"Learning to run a power network challenge for training topology controllers","created":"2019-12-05","cited_by_count":34},{"id":"1510.05880","title":"Safety-Constrained Reinforcement Learning for MDPs","created":"2015-10-20","cited_by_count":33},{"id":"1707.05878","title":"On-line Building Energy Optimization using Deep Reinforcement Learning","created":"2017-07-18","cited_by_count":27},{"id":"2006.14156","title":"Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings","created":"2020-06-25","cited_by_count":26},{"id":"2106.15200","title":"Action Set Based Policy Optimization for Safe Power Grid Management","created":"2021-06-29","cited_by_count":21},{"id":"1709.05077","title":"Transforming Cooling Optimization for Green Data Center via Deep Reinforcement Learning","created":"2017-09-15","cited_by_count":18},{"id":"1808.10427","title":"Reinforcement Learning Testbed for Power-Consumption Optimization","created":"2018-08-21","cited_by_count":18},{"id":"2103.07932","title":"Gym-ANM: Reinforcement Learning Environments for Active Network Management Tasks in Electricity Distribution Systems","created":"2021-03-14","cited_by_count":18},{"id":"2110.12908","title":"Learning to run a power network with trust","created":"2021-10-21","cited_by_count":17},{"id":"2301.08502","title":"Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning","created":"2023-01-20","cited_by_count":17},{"id":"2111.05969","title":"PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems","created":"2021-11-10","cited_by_count":16},{"id":"2304.00765","title":"Managing power grids through topology actions: A comparative study between advanced rule-based and reinforcement learning agents","created":"2023-04-03","cited_by_count":16},{"id":"2210.10391","title":"Machine Learning for a Sustainable Energy Future","created":"2022-10-19","cited_by_count":14},{"id":"2002.02581","title":"Dynamic Energy Dispatch Based on Deep Reinforcement Learning in IoT-Driven Smart Isolated Microgrids","created":"2020-02-07","cited_by_count":13},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13},{"id":"2303.06110","title":"Reinforcement Learning Versus Model Predictive Control on Greenhouse Climate Control","created":"2023-03-10","cited_by_count":12},{"id":"2102.09337","title":"Reinforcement Learning for Datacenter Congestion Control","created":"2021-02-18","cited_by_count":11},{"id":"2301.00641","title":"Federated Multi-Agent Deep Reinforcement Learning Approach via Physics-Informed Reward for Multi-Microgrid Energy Management","created":"2022-12-29","cited_by_count":11},{"id":"2307.11546","title":"Towards practical reinforcement learning for tokamak magnetic control","created":"2023-07-21","cited_by_count":9},{"id":"1904.10597","title":"Autonomous Voltage Control for Grid Operation Using Deep Reinforcement Learning","created":"2019-04-24","cited_by_count":8},{"id":"2111.10898","title":"Renewable energy integration and microgrid energy trading using multi-agent deep reinforcement learning","created":"2021-11-21","cited_by_count":8},{"id":"2211.03430","title":"A Federated DRL Approach for Smart Micro-Grid Energy Control with Distributed Energy Resources","created":"2022-11-07","cited_by_count":8},{"id":"2404.01849","title":"EV2Gym: A Flexible V2G Simulator for EV Smart Charging Research and Benchmarking","created":"2024-04-02","cited_by_count":8},{"id":"1909.08604","title":"ModelicaGym: Applying Reinforcement Learning to Modelica Models","created":"2019-09-18","cited_by_count":6},{"id":"2105.08846","title":"Gym-ANM: Open-source software to leverage reinforcement learning for power system management in research and education","created":"2021-05-18","cited_by_count":6},{"id":"2108.11645","title":"Robust Model-based Reinforcement Learning for Autonomous Greenhouse Control","created":"2021-08-26","cited_by_count":6},{"id":"2003.03327","title":"Smart Train Operation Algorithms based on Expert Knowledge and Reinforcement Learning","created":"2020-03-06","cited_by_count":5},{"id":"2111.11868","title":"Multi-agent Bayesian Deep Reinforcement Learning for Microgrid Energy Management under Communication Failures","created":"2021-11-22","cited_by_count":5},{"id":"2305.18875","title":"Centralised rehearsal of decentralised cooperation: Multi-agent reinforcement learning for the scalable coordination of residential energy flexibility","created":"2023-05-30","cited_by_count":5},{"id":"2007.05474","title":"A Reinforcement Learning Approach for Fast Frequency Control in Low-Inertia Power Systems","created":"2020-07-10","cited_by_count":4},{"id":"2103.06380","title":"Multi-Objective Reinforcement Learning based Multi-Microgrid System Optimisation Problem","created":"2021-03-10","cited_by_count":4},{"id":"2104.04080","title":"Design and implementation of an environment for Learning to Run a Power Network (L2RPN)","created":"2021-04-06","cited_by_count":4},{"id":"1603.01840","title":"Hierarchical Decision Making In Electricity Grid Management","created":"2016-03-06","cited_by_count":3},{"id":"2208.06385","title":"Low Emission Building Control with Zero-Shot Reinforcement Learning","created":"2022-08-12","cited_by_count":3},{"id":"2302.08328","title":"Learning a Multi-Agent Controller for Shared Energy Storage System","created":"2023-02-16","cited_by_count":3},{"id":"2303.08447","title":"MAHTM: A Multi-Agent Framework for Hierarchical Transactive Microgrids","created":"2023-03-15","cited_by_count":3},{"id":"2012.06458","title":"On Training Effective Reinforcement Learning Agents for Real-time Power Grid Operation and Control","created":"2020-12-11","cited_by_count":2},{"id":"2106.10360","title":"Prediction-Free, Real-Time Flexible Control of Tidal Lagoons through Proximal Policy Optimisation: A Case Study for the Swansea Lagoon","created":"2021-06-18","cited_by_count":2},{"id":"2212.04136","title":"Design and Planning of Flexible Mobile Micro-Grids Using Deep Reinforcement Learning","created":"2022-12-08","cited_by_count":2},{"id":"2303.05205","title":"Real-time scheduling of renewable power systems through planning-based reinforcement learning","created":"2023-03-09","cited_by_count":2},{"id":"2307.05812","title":"Safe Reinforcement Learning for Strategic Bidding of Virtual Power Plants in Day-Ahead Markets","created":"2023-07-11","cited_by_count":2},{"id":"2307.08401","title":"A Novel Multiagent Flexibility Aggregation Framework","created":"2023-07-17","cited_by_count":2},{"id":"2308.14924","title":"Optimal Economic Gas Turbine Dispatch with Deep Reinforcement Learning","created":"2023-08-28","cited_by_count":2},{"id":"2312.04371","title":"A Scalable Network-Aware Multi-Agent Reinforcement Learning Framework for Decentralized Inverter-based Voltage Control","created":"2023-12-07","cited_by_count":2},{"id":"2012.06312","title":"Deep Reinforcement Learning for Long Term Hydropower Production Scheduling","created":"2020-12-09","cited_by_count":1},{"id":"2204.04612","title":"Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching","created":"2022-04-10","cited_by_count":1},{"id":"2210.13555","title":"Energy Pricing in P2P Energy Systems Using Reinforcement Learning","created":"2022-10-24","cited_by_count":1},{"id":"2302.14094","title":"Combating Uncertainties in Wind and Distributed PV Energy Sources Using Integrated Reinforcement Learning and Time-Series Forecasting","created":"2023-02-27","cited_by_count":1},{"id":"2306.08147","title":"Multi-market Energy Optimization with Renewables via Reinforcement Learning","created":"2023-06-13","cited_by_count":1},{"id":"2311.02551","title":"High-dimensional Bid Learning for Energy Storage Bidding in Energy Markets","created":"2023-11-05","cited_by_count":1},{"id":"2311.18327","title":"Deep Reinforcement Learning Based Optimal Energy Management of Multi-energy Microgrids with Uncertainties","created":"2023-11-30","cited_by_count":1}],"next_cursor":null}