{"list":"other","total":50,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"1710.08864","title":"One pixel attack for fooling deep neural networks","created":"2017-10-24","cited_by_count":582},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"id":"1603.00448","title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","created":"2016-03-01","cited_by_count":406},{"id":"2003.04960","title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","created":"2020-03-10","cited_by_count":373},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"1805.07708","title":"A Lyapunov-based Approach to Safe Reinforcement Learning","created":"2018-05-20","cited_by_count":297},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1707.05300","title":"Reverse Curriculum Generation for Reinforcement Learning","created":"2017-07-17","cited_by_count":198},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"id":"1605.02097","title":"ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning","created":"2016-05-06","cited_by_count":179},{"id":"1802.10567","title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","created":"2018-02-28","cited_by_count":167},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"1511.01644","title":"Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model","created":"2015-11-05","cited_by_count":140},{"id":"1707.05173","title":"Trial without Error: Towards Safe Reinforcement Learning via Human Intervention","created":"2017-07-17","cited_by_count":103},{"id":"1604.07255","title":"A Deep Hierarchical Approach to Lifelong Learning in Minecraft","created":"2016-04-25","cited_by_count":90},{"id":"2005.02259","title":"Learning programs by learning from failures","created":"2020-05-05","cited_by_count":73},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73},{"id":"1810.08700","title":"Safe Reinforcement Learning with Model Uncertainty Estimates","created":"2018-10-19","cited_by_count":72},{"id":"1602.08610","title":"Scalable Bayesian Rule Lists","created":"2016-02-27","cited_by_count":64},{"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":"1607.03842","title":"Safe Policy Improvement by Minimizing Robust Baseline Regret","created":"2016-07-13","cited_by_count":53},{"id":"2103.10690","title":"Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Driving","created":"2021-03-19","cited_by_count":47},{"id":"1805.07830","title":"Learning to Teach in Cooperative Multiagent Reinforcement Learning","created":"2018-05-20","cited_by_count":45},{"id":"1402.0560","title":"Safe Exploration of State and Action Spaces in Reinforcement Learning","created":"2014-02-04","cited_by_count":38},{"id":"1901.07510","title":"Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target","created":"2019-01-22","cited_by_count":31},{"id":"1606.04695","title":"Strategic Attentive Writer for Learning Macro-Actions","created":"2016-06-15","cited_by_count":30},{"id":"2110.10963","title":"Neuro-Symbolic Reinforcement Learning with First-Order Logic","created":"2021-10-21","cited_by_count":30},{"id":"1706.03469","title":"Data-Efficient Policy Evaluation Through Behavior Policy Search","created":"2017-06-12","cited_by_count":26},{"id":"1804.00810","title":"StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer Learning","created":"2018-04-03","cited_by_count":25},{"id":"1510.02879","title":"Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain","created":"2015-10-10","cited_by_count":19},{"id":"1806.03793","title":"Context-Aware Policy Reuse","created":"2018-06-11","cited_by_count":16},{"id":"1709.08201","title":"An Optimal Online Method of Selecting Source Policies for Reinforcement Learning","created":"2017-09-24","cited_by_count":13},{"id":"2206.12493","title":"RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments","created":"2022-06-24","cited_by_count":13},{"id":"1907.04964","title":"A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning","created":"2019-07-11","cited_by_count":12},{"id":"2003.10386","title":"Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programming","created":"2020-03-23","cited_by_count":12},{"id":"1707.06658","title":"RAIL: Risk-Averse Imitation Learning","created":"2017-07-20","cited_by_count":9},{"id":"2106.11417","title":"Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming","created":"2021-06-21","cited_by_count":8},{"id":"1703.06905","title":"Learning to Navigate Cloth using Haptics","created":"2017-03-20","cited_by_count":4},{"id":"1912.12630","title":"Real-time Policy Distillation in Deep Reinforcement Learning","created":"2019-12-29","cited_by_count":4}],"next_cursor":null}