{"list":"other","total":52,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"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":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"1906.05113","title":"A Survey of Autonomous Driving: Common Practices and Emerging Technologies","created":"2019-06-12","cited_by_count":379},{"id":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"id":"1701.00160","title":"NIPS 2016 Tutorial: Generative Adversarial Networks","created":"2016-12-31","cited_by_count":285},{"id":"1906.04733","title":"DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections","created":"2019-06-10","cited_by_count":254},{"id":"1810.12429","title":"Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation","created":"2018-10-29","cited_by_count":227},{"id":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"1912.02074","title":"AlgaeDICE: Policy Gradient from Arbitrary Experience","created":"2019-12-04","cited_by_count":188},{"id":"1910.12809","title":"Minimax Weight and Q-Function Learning for Off-Policy Evaluation","created":"2019-10-28","cited_by_count":150},{"id":"1807.03858","title":"Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees","created":"2018-07-10","cited_by_count":140},{"id":"2002.09072","title":"GenDICE: Generalized Offline Estimation of Stationary Values","created":"2020-02-21","cited_by_count":122},{"id":"2006.03647","title":"Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization","created":"2020-06-05","cited_by_count":120},{"id":"1906.03393","title":"Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling","created":"2019-06-08","cited_by_count":119},{"id":"1908.08526","title":"Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes","created":"2019-08-22","cited_by_count":119},{"id":"1809.05214","title":"Model-Based Reinforcement Learning via Meta-Policy Optimization","created":"2018-09-14","cited_by_count":101},{"id":"2001.01866","title":"Reinforcement Learning via Fenchel-Rockafellar Duality","created":"2020-01-07","cited_by_count":100},{"id":"2002.04523","title":"Objective Mismatch in Model-based Reinforcement Learning","created":"2020-02-11","cited_by_count":96},{"id":"2007.03438","title":"Off-Policy Evaluation via the Regularized Lagrangian","created":"2020-07-07","cited_by_count":86},{"id":"1902.10250","title":"Diagnosing Bottlenecks in Deep Q-learning Algorithms","created":"2019-02-26","cited_by_count":73},{"id":"2004.07804","title":"A Game Theoretic Framework for Model Based Reinforcement Learning","created":"2020-04-16","cited_by_count":73},{"id":"2112.01573","title":"FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization","created":"2021-12-02","cited_by_count":71},{"id":"2010.11652","title":"CoinDICE: Off-Policy Confidence Interval Estimation","created":"2020-10-22","cited_by_count":64},{"id":"2010.10604","title":"Bayesian Attention Modules","created":"2020-10-20","cited_by_count":51},{"id":"1910.07186","title":"Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation","created":"2019-10-16","cited_by_count":48},{"id":"1905.10506","title":"A Kernel Loss for Solving the Bellman Equation","created":"2019-05-25","cited_by_count":37},{"id":"2008.06668","title":"Accountable Off-Policy Evaluation With Kernel Bellman Statistics","created":"2020-08-15","cited_by_count":36},{"id":"2110.02758","title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL","created":"2021-10-06","cited_by_count":36},{"id":"2204.01464","title":"Value Gradient weighted Model-Based Reinforcement Learning","created":"2022-04-04","cited_by_count":32},{"id":"2106.05251","title":"Bayesian Attention Belief Networks","created":"2021-06-09","cited_by_count":25},{"id":"2205.04980","title":"ALLSH: Active Learning Guided by Local Sensitivity and Hardness","created":"2022-05-10","cited_by_count":23},{"id":"2012.14100","title":"Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions","created":"2020-12-28","cited_by_count":22},{"id":"1805.09044","title":"Representation Balancing MDPs for Off-Policy Policy Evaluation","created":"2018-05-23","cited_by_count":20},{"id":"1909.04115","title":"Gradient-Aware Model-based Policy Search","created":"2019-09-09","cited_by_count":19},{"id":"2003.00722","title":"Batch Stationary Distribution Estimation","created":"2020-03-02","cited_by_count":19},{"id":"2003.11126","title":"Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning","created":"2020-03-24","cited_by_count":16},{"id":"2007.06159","title":"Implicit Distributional Reinforcement Learning","created":"2020-07-13","cited_by_count":16},{"id":"2103.02084","title":"Minimax Model Learning","created":"2021-03-02","cited_by_count":16},{"id":"2110.12567","title":"Alignment Attention by Matching Key and Query Distributions","created":"2021-10-25","cited_by_count":14},{"id":"2103.05741","title":"Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual Bounds","created":"2021-03-09","cited_by_count":11},{"id":"2010.15392","title":"Off-Policy Interval Estimation with Lipschitz Value Iteration","created":"2020-10-29","cited_by_count":4}],"next_cursor":null}