{"list":"other","total":60,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"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":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"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":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1708.02596","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","created":"2017-08-08","cited_by_count":297},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253},{"id":"1803.00653","title":"Semi-parametric Topological Memory for Navigation","created":"2018-03-01","cited_by_count":209},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"1901.09184","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","created":"2019-01-26","cited_by_count":174},{"id":"1602.02867","title":"Value Iteration Networks","created":"2016-02-09","cited_by_count":160},{"id":"1911.08453","title":"Planning with Goal-Conditioned Policies","created":"2019-11-19","cited_by_count":149},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"2304.01203","title":"Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning","created":"2023-04-03","cited_by_count":121},{"id":"1810.00123","title":"Generalization and Regularization in DQN","created":"2018-09-29","cited_by_count":118},{"id":"2003.06085","title":"Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations","created":"2020-03-13","cited_by_count":115},{"id":"1811.01848","title":"Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control","created":"2018-11-05","cited_by_count":113},{"id":"1910.12911","title":"Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck","created":"2019-10-28","cited_by_count":101},{"id":"2101.02722","title":"The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels","created":"2021-01-07","cited_by_count":100},{"id":"2202.04478","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","created":"2022-02-09","cited_by_count":89},{"id":"1806.10729","title":"Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation","created":"2018-06-28","cited_by_count":81},{"id":"1909.10618","title":"Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?","created":"2019-09-23","cited_by_count":68},{"id":"2206.03023","title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression","created":"2022-06-07","cited_by_count":66},{"id":"1804.03720","title":"Gotta Learn Fast: A New Benchmark for Generalization in RL","created":"2018-04-10","cited_by_count":59},{"id":"2202.11271","title":"ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints","created":"2022-02-23","cited_by_count":58},{"id":"1811.07819","title":"Learning Actionable Representations with Goal-Conditioned Policies","created":"2018-11-19","cited_by_count":54},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43},{"id":"2204.13060","title":"Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning","created":"2022-04-27","cited_by_count":38},{"id":"1806.06408","title":"Gated Path Planning Networks","created":"2018-06-17","cited_by_count":31},{"id":"2106.07278","title":"Which Mutual-Information Representation Learning Objectives are Sufficient for Control?","created":"2021-06-14","cited_by_count":29},{"id":"2106.13229","title":"Model-Based Reinforcement Learning via Latent-Space Collocation","created":"2021-06-24","cited_by_count":28},{"id":"2002.05825","title":"An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality","created":"2020-02-14","cited_by_count":24},{"id":"2211.15120","title":"Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings","created":"2022-11-28","cited_by_count":24},{"id":"2306.14808","title":"Maximum State Entropy Exploration using Predecessor and Successor Representations","created":"2023-06-26","cited_by_count":23},{"id":"1904.05869","title":"Keyframing the Future: Keyframe Discovery for Visual Prediction and Planning","created":"2019-04-11","cited_by_count":20},{"id":"2004.11410","title":"Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning","created":"2020-04-23","cited_by_count":19},{"id":"2408.16228","title":"Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation","created":"2024-08-29","cited_by_count":18},{"id":"2110.12080","title":"C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks","created":"2021-10-22","cited_by_count":17},{"id":"2403.04082","title":"Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference","created":"2024-03-06","cited_by_count":17},{"id":"2206.15478","title":"On the Learning and Learnability of Quasimetrics","created":"2022-06-30","cited_by_count":15},{"id":"2002.06473","title":"Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning","created":"2020-02-15","cited_by_count":12},{"id":"2212.04581","title":"PALMER: Perception-Action Loop with Memory for Long-Horizon Planning","created":"2022-12-08","cited_by_count":5}],"next_cursor":null}