{"list":"other","total":54,"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":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"1611.09940","title":"Neural Combinatorial Optimization with Reinforcement Learning","created":"2016-11-29","cited_by_count":608},{"id":"1904.07272","title":"Introduction to Multi-Armed Bandits","created":"2019-04-15","cited_by_count":481},{"id":"1707.02038","title":"A Tutorial on Thompson Sampling","created":"2017-07-07","cited_by_count":433},{"id":"1710.08005","title":"Smart \"Predict, then Optimize\"","created":"2017-10-22","cited_by_count":339},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279},{"id":"1705.08439","title":"Thinking Fast and Slow with Deep Learning and Tree Search","created":"2017-05-23","cited_by_count":252},{"id":"2112.13487","title":"The Statistical Complexity of Interactive Decision Making","created":"2021-12-27","cited_by_count":218},{"id":"1802.05399","title":"Competitive caching with machine learned advice","created":"2018-02-15","cited_by_count":195},{"id":"1810.01963","title":"Learning Scheduling Algorithms for Data Processing Clusters","created":"2018-10-03","cited_by_count":134},{"id":"1406.5979","title":"Reinforcement and Imitation Learning via Interactive No-Regret Learning","created":"2014-06-23","cited_by_count":118},{"id":"1906.04859","title":"Reinforcement Learning for Integer Programming: Learning to Cut","created":"2019-06-11","cited_by_count":111},{"id":"2202.02446","title":"Adversarially Trained Actor Critic for Offline Reinforcement Learning","created":"2022-02-05","cited_by_count":111},{"id":"1912.02877","title":"Training Agents using Upside-Down Reinforcement Learning","created":"2019-12-05","cited_by_count":107},{"id":"2010.03531","title":"Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited","created":"2020-10-07","cited_by_count":106},{"id":"1606.03203","title":"Causal Bandits: Learning Good Interventions via Causal Inference","created":"2016-06-10","cited_by_count":101},{"id":"1703.01030","title":"Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction","created":"2017-03-03","cited_by_count":93},{"id":"2011.09464","title":"Counterfactual Credit Assignment in Model-Free Reinforcement Learning","created":"2020-11-18","cited_by_count":64},{"id":"2008.06319","title":"OR-Gym: A Reinforcement Learning Library for Operations Research Problems","created":"2020-08-14","cited_by_count":51},{"id":"2106.02757","title":"Heuristic-Guided Reinforcement Learning","created":"2021-06-05","cited_by_count":42},{"id":"2008.01644","title":"Queueing Network Controls via Deep Reinforcement Learning","created":"2020-07-31","cited_by_count":41},{"id":"1708.05930","title":"Solving a New 3D Bin Packing Problem with Deep Reinforcement Learning Method","created":"2017-08-20","cited_by_count":31},{"id":"1807.02264","title":"Variance Reduction for Reinforcement Learning in Input-Driven Environments","created":"2018-07-06","cited_by_count":30},{"id":"2103.10860","title":"Universal Trading for Order Execution with Oracle Policy Distillation","created":"2021-01-28","cited_by_count":30},{"id":"2206.04282","title":"Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information","created":"2022-06-09","cited_by_count":26},{"id":"1806.01584","title":"Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning","created":"2018-06-05","cited_by_count":24},{"id":"2012.15566","title":"Robust Asymmetric Learning in POMDPs","created":"2020-12-31","cited_by_count":23},{"id":"1301.3878","title":"PEGASUS: A Policy Search Method for Large MDPs and POMDPs","created":"2013-01-16","cited_by_count":22},{"id":"1905.04337","title":"Learning in structured MDPs with convex cost functions: Improved regret bounds for inventory management","created":"2019-05-10","cited_by_count":22},{"id":"1906.06361","title":"Online Allocation and Pricing: Constant Regret via Bellman Inequalities","created":"2019-06-14","cited_by_count":16},{"id":"1910.08151","title":"Adaptive Discretization for Episodic Reinforcement Learning in Metric Spaces","created":"2019-10-17","cited_by_count":16},{"id":"1804.00846","title":"Learning to Search via Retrospective Imitation","created":"2018-04-03","cited_by_count":14},{"id":"1901.05028","title":"The Bayesian Prophet: A Low-Regret Framework for Online Decision Making","created":"2019-01-15","cited_by_count":13},{"id":"2011.12354","title":"PowerNet: Multi-agent Deep Reinforcement Learning for Scalable Powergrid Control","created":"2020-11-24","cited_by_count":13},{"id":"2009.14679","title":"Scalable Deep Reinforcement Learning for Ride-Hailing","created":"2020-09-27","cited_by_count":12},{"id":"1909.13870","title":"Learning Compact Models for Planning with Exogenous Processes","created":"2019-09-30","cited_by_count":11},{"id":"1709.00503","title":"Mean Actor Critic","created":"2017-09-01","cited_by_count":8},{"id":"2105.14388","title":"Dynamic Placement in Refugee Resettlement","created":"2021-05-29","cited_by_count":7},{"id":"2107.12216","title":"Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment","created":"2021-07-26","cited_by_count":7},{"id":"1912.02222","title":"Reinforcement learning for bandwidth estimation and congestion control in real-time communications","created":"2019-12-04","cited_by_count":6},{"id":"2007.03069","title":"Outcome-Driven Dynamic Refugee Assignment with Allocation Balancing","created":"2020-07-02","cited_by_count":6},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","cited_by_count":6},{"id":"2110.10081","title":"Stateful Offline Contextual Policy Evaluation and Learning","created":"2021-10-19","cited_by_count":6},{"id":"1612.03161","title":"Prophet Inequalities Made Easy: Stochastic Optimization by Pricing Non-Stochastic Inputs","created":"2016-12-09","cited_by_count":5},{"id":"2006.15690","title":"Lookahead-Bounded Q-Learning","created":"2020-06-28","cited_by_count":5},{"id":"1606.00957","title":"Optimality Conditions for Inventory Control","created":"2016-06-03","cited_by_count":3},{"id":"2102.10474","title":"Towards the k-server conjecture: A unifying potential, pushing the frontier to the circle","created":"2021-02-20","cited_by_count":3},{"id":"1511.09437","title":"Distributionally robust inventory control when demand is a martingale","created":"2015-11-30","cited_by_count":2},{"id":"2112.04785","title":"VMAgent: Scheduling Simulator for Reinforcement Learning","created":"2021-12-09","cited_by_count":2}],"next_cursor":null}