{"list":"other","total":61,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"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":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"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":"1505.04366","title":"Learning Deconvolution Network for Semantic Segmentation","created":"2015-05-17","cited_by_count":365},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","cited_by_count":209},{"id":"2010.07922","title":"Representation Learning via Invariant Causal Mechanisms","created":"2020-10-15","cited_by_count":199},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"2102.11271","title":"Reinforcement Learning with Prototypical Representations","created":"2021-02-22","cited_by_count":179},{"id":"1510.09142","title":"Learning Continuous Control Policies by Stochastic Value Gradients","created":"2015-10-30","cited_by_count":162},{"id":"1907.02057","title":"Benchmarking Model-Based Reinforcement Learning","created":"2019-07-03","cited_by_count":162},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"1707.06203","title":"Imagination-Augmented Agents for Deep Reinforcement Learning","created":"2017-07-19","cited_by_count":140},{"id":"2009.04416","title":"Phasic Policy Gradient","created":"2020-09-09","cited_by_count":123},{"id":"2004.14646","title":"Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning","created":"2020-04-30","cited_by_count":102},{"id":"1910.12911","title":"Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck","created":"2019-10-28","cited_by_count":101},{"id":"2007.08558","title":"On Robustness and Transferability of Convolutional Neural Networks","created":"2020-07-16","cited_by_count":98},{"id":"2011.03506","title":"The Value Equivalence Principle for Model-Based Reinforcement Learning","created":"2020-11-06","cited_by_count":94},{"id":"2104.06294","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","created":"2021-04-13","cited_by_count":90},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82},{"id":"1806.10729","title":"Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation","created":"2018-06-28","cited_by_count":81},{"id":"2006.07217","title":"Deep Reinforcement and InfoMax Learning","created":"2020-06-12","cited_by_count":79},{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77},{"id":"1806.01830","title":"Relational Deep Reinforcement Learning","created":"2018-06-05","cited_by_count":73},{"id":"2006.12862","title":"Automatic Data Augmentation for Generalization in Deep Reinforcement Learning","created":"2020-06-23","cited_by_count":71},{"id":"1910.04098","title":"Improving Generalization in Meta Reinforcement Learning using Learned Objectives","created":"2019-10-09","cited_by_count":68},{"id":"1901.03559","title":"An investigation of model-free planning","created":"2019-01-11","cited_by_count":66},{"id":"1906.09237","title":"Shaping Belief States with Generative Environment Models for RL","created":"2019-06-21","cited_by_count":66},{"id":"2007.12509","title":"Monte-Carlo Tree Search as Regularized Policy Optimization","created":"2020-07-24","cited_by_count":61},{"id":"1804.03720","title":"Gotta Learn Fast: A New Benchmark for Generalization in RL","created":"2018-04-10","cited_by_count":59},{"id":"2011.04021","title":"On the role of planning in model-based deep reinforcement learning","created":"2020-11-08","cited_by_count":57},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53},{"id":"1904.03177","title":"Structured agents for physical construction","created":"2019-04-05","cited_by_count":50},{"id":"2106.04615","title":"Vector Quantized Models for Planning","created":"2021-06-08","cited_by_count":48},{"id":"1811.06407","title":"Neural Predictive Belief Representations","created":"2018-11-15","cited_by_count":40},{"id":"1811.06032","title":"Natural Environment Benchmarks for Reinforcement Learning","created":"2018-11-14","cited_by_count":32},{"id":"2006.08170","title":"MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration","created":"2020-06-15","cited_by_count":25},{"id":"2002.02836","title":"Causally Correct Partial Models for Reinforcement Learning","created":"2020-02-07","cited_by_count":24},{"id":"2103.15332","title":"Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark","created":"2021-03-29","cited_by_count":23},{"id":"1803.00512","title":"Composable Planning with Attributes","created":"2018-03-01","cited_by_count":21},{"id":"2107.05431","title":"CoBERL: Contrastive BERT for Reinforcement Learning","created":"2021-07-12","cited_by_count":21},{"id":"1812.02868","title":"Measuring and Characterizing Generalization in Deep Reinforcement Learning","created":"2018-12-07","cited_by_count":20},{"id":"2106.02193","title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL","created":"2021-06-04","cited_by_count":20}],"next_cursor":null}