{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"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":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1806.06877","title":"A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress","created":"2018-06-18","cited_by_count":298},{"id":"2102.09544","title":"Combinatorial optimization and reasoning with graph neural networks","created":"2021-02-18","cited_by_count":268},{"id":"1801.00631","title":"Deep Learning: A Critical Appraisal","created":"2018-01-02","cited_by_count":217},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","cited_by_count":209},{"id":"1711.03902","title":"Neural-Symbolic Learning and Reasoning: A Survey and Interpretation","created":"2017-11-10","cited_by_count":196},{"id":"1602.02867","title":"Value Iteration Networks","created":"2016-02-09","cited_by_count":160},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"1904.11694","title":"Neural Logic Machines","created":"2019-04-26","cited_by_count":145},{"id":"1612.00341","title":"A Compositional Object-Based Approach to Learning Physical Dynamics","created":"2016-12-01","cited_by_count":119},{"id":"1707.03497","title":"Value Prediction Network","created":"2017-07-11","cited_by_count":117},{"id":"1703.00956","title":"A Laplacian Framework for Option Discovery in Reinforcement Learning","created":"2017-03-02","cited_by_count":110},{"id":"2011.03506","title":"The Value Equivalence Principle for Model-Based Reinforcement Learning","created":"2020-11-06","cited_by_count":94},{"id":"1612.08810","title":"The Predictron: End-To-End Learning and Planning","created":"2016-12-28","cited_by_count":93},{"id":"1401.3839","title":"The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarks","created":"2014-01-16","cited_by_count":87},{"id":"1708.02190","title":"Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning","created":"2017-08-07","cited_by_count":83},{"id":"1811.00090","title":"SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning","created":"2018-10-31","cited_by_count":78},{"id":"1704.02254","title":"Recurrent Environment Simulators","created":"2017-04-07","cited_by_count":68},{"id":"1901.03559","title":"An investigation of model-free planning","created":"2019-01-11","cited_by_count":66},{"id":"1706.04317","title":"Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics","created":"2017-06-14","cited_by_count":58},{"id":"2003.10014","title":"Reinforcement Learning in Economics and Finance","created":"2020-03-22","cited_by_count":58},{"id":"1804.07779","title":"PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making","created":"2018-04-20","cited_by_count":52},{"id":"1911.13101","title":"Learning Domain-Independent Planning Heuristics with Hypergraph Networks","created":"2019-11-29","cited_by_count":50},{"id":"1605.07127","title":"Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks","created":"2016-05-23","cited_by_count":49},{"id":"1611.01843","title":"Learning to Perform Physics Experiments via Deep Reinforcement Learning","created":"2016-11-06","cited_by_count":47},{"id":"1502.02251","title":"From Pixels to Torques: Policy Learning with Deep Dynamical Models","created":"2015-02-08","cited_by_count":45},{"id":"2002.11697","title":"The Emerging Landscape of Explainable AI Planning and Decision Making","created":"2020-02-26","cited_by_count":44},{"id":"1609.05518","title":"Towards Deep Symbolic Reinforcement Learning","created":"2016-09-18","cited_by_count":42},{"id":"2006.16712","title":"Model-based Reinforcement Learning: A Survey","created":"2020-06-30","cited_by_count":39},{"id":"1802.04697","title":"Learning to Search with MCTSnets","created":"2018-02-13","cited_by_count":33},{"id":"1709.04271","title":"Action Schema Networks: Generalised Policies with Deep Learning","created":"2017-09-13","cited_by_count":32},{"id":"1707.06170","title":"Learning model-based planning from scratch","created":"2017-07-19","cited_by_count":22},{"id":"2107.00110","title":"Classical Planning in Deep Latent Space","created":"2021-06-30","cited_by_count":22},{"id":"1904.11739","title":"Landmark-Based Approaches for Goal Recognition as Planning","created":"2019-04-26","cited_by_count":21},{"id":"2109.14830","title":"Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators","created":"2021-09-30","cited_by_count":21},{"id":"1807.01521","title":"Curiosity Driven Exploration of Learned Disentangled Goal Spaces","created":"2018-07-04","cited_by_count":16},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13},{"id":"1710.11417","title":"TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning","created":"2017-10-31","cited_by_count":12},{"id":"1811.00128","title":"Towards a Simple Approach to Multi-step Model-based Reinforcement Learning","created":"2018-10-31","cited_by_count":9},{"id":"1301.6704","title":"SPUDD: Stochastic Planning using Decision Diagrams","created":"2013-01-23","cited_by_count":7},{"id":"1702.04649","title":"Generative Temporal Models with Memory","created":"2017-02-15","cited_by_count":6},{"id":"2207.01911","title":"Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applications","created":"2022-07-05","cited_by_count":6},{"id":"2301.10280","title":"NeSIG: A Neuro-Symbolic Method for Learning to Generate Planning Problems","created":"2023-01-24","cited_by_count":6},{"id":"2006.15009","title":"A Unifying Framework for Reinforcement Learning and Planning","created":"2020-06-26","cited_by_count":4}],"next_cursor":null}