{"list":"other","total":62,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"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":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1704.04289","title":"Stochastic Gradient Descent as Approximate Bayesian Inference","created":"2017-04-13","cited_by_count":300},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1802.09464","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","created":"2018-02-26","cited_by_count":260},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"1704.03003","title":"Automated Curriculum Learning for Neural Networks","created":"2017-04-10","cited_by_count":257},{"id":"1707.00183","title":"Teacher-Student Curriculum Learning","created":"2017-07-01","cited_by_count":210},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"1606.01885","title":"Learning to Optimize","created":"2016-06-06","cited_by_count":195},{"id":"1905.12588","title":"Meta-Learning Representations for Continual Learning","created":"2019-05-29","cited_by_count":189},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173},{"id":"1805.09801","title":"Meta-Gradient Reinforcement Learning","created":"2018-05-24","cited_by_count":159},{"id":"1910.07224","title":"Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments","created":"2019-10-16","cited_by_count":119},{"id":"2002.00632","title":"Effective Diversity in Population Based Reinforcement Learning","created":"2020-02-03","cited_by_count":119},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111},{"id":"1909.00025","title":"Meta-Learning with Warped Gradient Descent","created":"2019-08-30","cited_by_count":98},{"id":"1707.06386","title":"Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains","created":"2017-07-20","cited_by_count":88},{"id":"2006.12122","title":"Learning with AMIGo: Adversarially Motivated Intrinsic Goals","created":"2020-06-22","cited_by_count":88},{"id":"2003.12613","title":"Adaptive Reward-Poisoning Attacks against Reinforcement Learning","created":"2020-03-27","cited_by_count":86},{"id":"1803.02021","title":"Understanding Short-Horizon Bias in Stochastic Meta-Optimization","created":"2018-03-06","cited_by_count":69},{"id":"1906.04724","title":"Large Scale Structure of Neural Network Loss Landscapes","created":"2019-06-11","cited_by_count":68},{"id":"1801.05927","title":"An Overview of Machine Teaching","created":"2018-01-18","cited_by_count":63},{"id":"1907.02911","title":"Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape","created":"2019-07-05","cited_by_count":63},{"id":"2006.16318","title":"Learning and Planning in Average-Reward Markov Decision Processes","created":"2020-06-29","cited_by_count":54},{"id":"2109.02869","title":"The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning","created":"2021-09-07","cited_by_count":50},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45},{"id":"1810.02513","title":"Learning To Simulate","created":"2018-10-05","cited_by_count":44},{"id":"1703.00441","title":"Learning to Optimize Neural Nets","created":"2017-03-01","cited_by_count":41},{"id":"1810.12081","title":"Learning to Teach with Dynamic Loss Functions","created":"2018-10-29","cited_by_count":40},{"id":"1906.11527","title":"Hyp-RL : Hyperparameter Optimization by Reinforcement Learning","created":"2019-06-27","cited_by_count":36},{"id":"1812.00285","title":"Learning Curriculum Policies for Reinforcement Learning","created":"2018-12-01","cited_by_count":35},{"id":"1905.05895","title":"Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment","created":"2019-05-15","cited_by_count":33},{"id":"1805.07687","title":"Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications","created":"2018-05-20","cited_by_count":28},{"id":"2002.11833","title":"Policy Evaluation Networks","created":"2020-02-26","cited_by_count":28},{"id":"1904.06979","title":"A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms","created":"2019-04-15","cited_by_count":27},{"id":"2006.09226","title":"Parameter-Based Value Functions","created":"2020-06-16","cited_by_count":24},{"id":"2106.00958","title":"A Generalizable Approach to Learning Optimizers","created":"2021-06-02","cited_by_count":23},{"id":"1310.3174","title":"Multi-Armed Bandits for Intelligent Tutoring Systems","created":"2013-10-11","cited_by_count":21},{"id":"1902.00843","title":"A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning","created":"2019-02-03","cited_by_count":18},{"id":"2104.11353","title":"Optimal Cost Design for Model Predictive Control","created":"2021-04-23","cited_by_count":13},{"id":"2103.09159","title":"Learning to Shape Rewards using a Game of Two Partners","created":"2021-03-16","cited_by_count":9},{"id":"2202.09701","title":"A History of Meta-gradient: Gradient Methods for Meta-learning","created":"2022-02-20","cited_by_count":7},{"id":"1804.03334","title":"TIDBD: Adapting Temporal-difference Step-sizes Through Stochastic Meta-descent","created":"2018-04-10","cited_by_count":5}],"next_cursor":null}