{"list":"other","total":85,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2304.10573","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","created":"2023-04-20","cited_by_count":325},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"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":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"1907.13440","title":"MineRL: A Large-Scale Dataset of Minecraft Demonstrations","created":"2019-07-29","cited_by_count":215},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2305.16300","title":"Landmark Attention: Random-Access Infinite Context Length for Transformers","created":"2023-05-25","cited_by_count":213},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170},{"id":"2011.13389","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","created":"2020-11-26","cited_by_count":137},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123},{"id":"1810.00123","title":"Generalization and Regularization in DQN","created":"2018-09-29","cited_by_count":118},{"id":"2103.07945","title":"Learning One Representation to Optimize All Rewards","created":"2021-03-14","cited_by_count":115},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111},{"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":"2003.06016","title":"Invariant Causal Prediction for Block MDPs","created":"2020-03-12","cited_by_count":105},{"id":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105},{"id":"1910.05396","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","created":"2019-10-11","cited_by_count":104},{"id":"1910.12911","title":"Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck","created":"2019-10-28","cited_by_count":101},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97},{"id":"2008.06043","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","created":"2020-08-13","cited_by_count":93},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93},{"id":"1912.02975","title":"Observational Overfitting in Reinforcement Learning","created":"2019-12-06","cited_by_count":91},{"id":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"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":"2010.10814","title":"Improving Generalization in Reinforcement Learning with Mixture Regularization","created":"2020-10-21","cited_by_count":81},{"id":"2006.07217","title":"Deep Reinforcement and InfoMax Learning","created":"2020-06-12","cited_by_count":79},{"id":"2010.14484","title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL","created":"2020-10-27","cited_by_count":79},{"id":"2006.05826","title":"Transient Non-Stationarity and Generalisation in Deep Reinforcement Learning","created":"2020-06-10","cited_by_count":75},{"id":"1703.02660","title":"Towards Generalization and Simplicity in Continuous Control","created":"2017-03-08","cited_by_count":68},{"id":"1804.03720","title":"Gotta Learn Fast: A New Benchmark for Generalization in RL","created":"2018-04-10","cited_by_count":59},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","cited_by_count":58},{"id":"1902.01378","title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","created":"2019-02-04","cited_by_count":54},{"id":"2107.03974","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","created":"2021-07-08","cited_by_count":53},{"id":"2003.06350","title":"Interference and Generalization in Temporal Difference Learning","created":"2020-03-13","cited_by_count":42},{"id":"2110.04276","title":"Offline Meta-Reinforcement Learning for Industrial Insertion","created":"2021-10-08","cited_by_count":39},{"id":"2006.01096","title":"Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learning","created":"2020-06-01","cited_by_count":37},{"id":"2305.18882","title":"What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?","created":"2023-05-30","cited_by_count":36},{"id":"2102.13268","title":"DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck","created":"2021-02-26","cited_by_count":31},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31},{"id":"2107.08828","title":"Reinforcement Learning for Education: Opportunities and Challenges","created":"2021-07-15","cited_by_count":25},{"id":"2001.09908","title":"Rotation, Translation, and Cropping for Zero-Shot Generalization","created":"2020-01-27","cited_by_count":24},{"id":"2010.06740","title":"Measuring Visual Generalization in Continuous Control from Pixels","created":"2020-10-13","cited_by_count":21},{"id":"2011.01089","title":"Instance based Generalization in Reinforcement Learning","created":"2020-11-02","cited_by_count":17},{"id":"2210.06479","title":"Real World Offline Reinforcement Learning with Realistic Data Source","created":"2022-10-12","cited_by_count":17},{"id":"2210.13417","title":"Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds","created":"2022-10-24","cited_by_count":17},{"id":"2211.00539","title":"Dungeons and Data: A Large-Scale NetHack Dataset","created":"2022-11-01","cited_by_count":16},{"id":"1705.10998","title":"The Atari Grand Challenge Dataset","created":"2017-05-31","cited_by_count":14},{"id":"2004.12399","title":"Reinforcement Learning Generalization with Surprise Minimization","created":"2020-04-26","cited_by_count":10},{"id":"2211.13051","title":"Powderworld: A Platform for Understanding Generalization via Rich Task Distributions","created":"2022-11-23","cited_by_count":6},{"id":"2006.03465","title":"Visual Transfer for Reinforcement Learning via Wasserstein Domain Confusion","created":"2020-06-04","cited_by_count":5},{"id":"2102.08581","title":"Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning","created":"2021-02-17","cited_by_count":3},{"id":"2308.15550","title":"Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning","created":"2023-08-29","cited_by_count":2}],"next_cursor":null}