{"list":"other","total":67,"rows":[{"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":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"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":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"1707.00183","title":"Teacher-Student Curriculum Learning","created":"2017-07-01","cited_by_count":210},{"id":"1906.02736","title":"DeepMDP: Learning Continuous Latent Space Models for Representation Learning","created":"2019-06-06","cited_by_count":207},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"1906.05253","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","created":"2019-06-12","cited_by_count":194},{"id":"2102.11271","title":"Reinforcement Learning with Prototypical Representations","created":"2021-02-22","cited_by_count":179},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170},{"id":"1901.09018","title":"Provably efficient RL with Rich Observations via Latent State Decoding","created":"2019-01-25","cited_by_count":169},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158},{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135},{"id":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109},{"id":"2005.06800","title":"Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning","created":"2020-05-14","cited_by_count":98},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97},{"id":"1308.3513","title":"Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations","created":"2013-08-15","cited_by_count":70},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70},{"id":"1710.04725","title":"Hyperparameter Importance Across Datasets","created":"2017-10-12","cited_by_count":63},{"id":"2002.02518","title":"Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits","created":"2020-02-06","cited_by_count":63},{"id":"2102.13651","title":"On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning","created":"2021-02-26","cited_by_count":59},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","cited_by_count":58},{"id":"1711.05726","title":"Markov Decision Processes with Continuous Side Information","created":"2017-11-15","cited_by_count":56},{"id":"1902.01378","title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","created":"2019-02-04","cited_by_count":54},{"id":"2004.11812","title":"Self-Paced Deep Reinforcement Learning","created":"2020-04-24","cited_by_count":50},{"id":"2107.07599","title":"Partially Observable Markov Decision Processes (POMDPs) and Robotics","created":"2021-07-15","cited_by_count":49},{"id":"1907.11740","title":"Environment Probing Interaction Policies","created":"2019-07-26","cited_by_count":39},{"id":"2102.02926","title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","created":"2021-02-04","cited_by_count":36},{"id":"2009.01555","title":"Sample-Efficient Automated Deep Reinforcement Learning","created":"2020-09-03","cited_by_count":32},{"id":"1812.11951","title":"Learning to Design RNA","created":"2018-12-31","cited_by_count":29},{"id":"2009.13891","title":"Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning","created":"2020-09-29","cited_by_count":29},{"id":"2106.05110","title":"Self-Paced Context Evaluation for Contextual Reinforcement Learning","created":"2021-06-09","cited_by_count":25},{"id":"1811.09083","title":"Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning","created":"2018-11-22","cited_by_count":24},{"id":"1903.00714","title":"A Cooperative Multi-Agent Reinforcement Learning Framework for Resource Balancing in Complex Logistics Network","created":"2019-03-02","cited_by_count":22},{"id":"2008.01531","title":"TOAD-GAN: Coherent Style Level Generation from a Single Example","created":"2020-08-04","cited_by_count":22},{"id":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","cited_by_count":20},{"id":"2105.09452","title":"Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection","created":"2021-05-20","cited_by_count":18},{"id":"2010.13483","title":"High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards","created":"2020-10-26","cited_by_count":14},{"id":"2107.08426","title":"A New Representation of Successor Features for Transfer across Dissimilar Environments","created":"2021-07-18","cited_by_count":13}],"next_cursor":null}