{"list":"other","total":74,"rows":[{"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":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1804.02477","title":"Programmatically Interpretable Reinforcement Learning","created":"2018-04-06","cited_by_count":193},{"id":"2010.03950","title":"Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning","created":"2020-10-06","cited_by_count":191},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","cited_by_count":177},{"id":"1612.03471","title":"Reinforcement Learning With Temporal Logic Rewards","created":"2016-12-11","cited_by_count":117},{"id":"1811.00090","title":"SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning","created":"2018-10-31","cited_by_count":78},{"id":"1909.05304","title":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees","created":"2019-09-11","cited_by_count":77},{"id":"1909.07299","title":"Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning","created":"2019-09-16","cited_by_count":75},{"id":"2102.06858","title":"LTL2Action: Generalizing LTL Instructions for Multi-Task RL","created":"2021-02-13","cited_by_count":74},{"id":"1806.01830","title":"Relational Deep Reinforcement Learning","created":"2018-06-05","cited_by_count":73},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73},{"id":"1807.06333","title":"Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specifications","created":"2018-07-17","cited_by_count":72},{"id":"2008.09293","title":"A Composable Specification Language for Reinforcement Learning Tasks","created":"2020-08-21","cited_by_count":69},{"id":"1609.07409","title":"Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications","created":"2016-09-23","cited_by_count":67},{"id":"1704.04341","title":"Environment-Independent Task Specifications via GLTL","created":"2017-04-14","cited_by_count":67},{"id":"2106.13906","title":"Compositional Reinforcement Learning from Logical Specifications","created":"2021-06-25","cited_by_count":67},{"id":"2101.11196","title":"Safe Multi-Agent Reinforcement Learning via Shielding","created":"2021-01-27","cited_by_count":61},{"id":"2108.13643","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","created":"2021-08-31","cited_by_count":59},{"id":"1909.05912","title":"Joint Inference of Reward Machines and Policies for Reinforcement Learning","created":"2019-09-12","cited_by_count":56},{"id":"2204.00755","title":"Safe Reinforcement Learning via Shielding under Partial Observability","created":"2022-04-02","cited_by_count":56},{"id":"1904.10729","title":"Neural Logic Reinforcement Learning","created":"2019-04-24","cited_by_count":53},{"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":"1801.08099","title":"Logically-Constrained Reinforcement Learning","created":"2018-01-24","cited_by_count":51},{"id":"2009.12612","title":"Neurosymbolic Reinforcement Learning with Formally Verified Exploration","created":"2020-09-26","cited_by_count":49},{"id":"1712.04170","title":"Interpretable Policies for Reinforcement Learning by Genetic Programming","created":"2017-12-12","cited_by_count":48},{"id":"2001.01394","title":"A Boolean Task Algebra for Reinforcement Learning","created":"2020-01-06","cited_by_count":48},{"id":"2002.12156","title":"Cautious Reinforcement Learning with Logical Constraints","created":"2020-02-26","cited_by_count":45},{"id":"2101.07393","title":"Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning","created":"2021-01-19","cited_by_count":45},{"id":"1902.00778","title":"Certified Reinforcement Learning with Logic Guidance","created":"2019-02-02","cited_by_count":36},{"id":"2006.01110","title":"Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas","created":"2020-06-01","cited_by_count":36},{"id":"2007.01962","title":"Reward Machines for Cooperative Multi-Agent Reinforcement Learning","created":"2020-07-03","cited_by_count":35},{"id":"2007.01223","title":"Verifiably Safe Exploration for End-to-End Reinforcement Learning","created":"2020-07-02","cited_by_count":34},{"id":"1510.05880","title":"Safety-Constrained Reinforcement Learning for MDPs","created":"2015-10-20","cited_by_count":33},{"id":"1909.04256","title":"Transfer of Temporal Logic Formulas in Reinforcement Learning","created":"2019-09-10","cited_by_count":31},{"id":"2007.01498","title":"Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks","created":"2020-07-03","cited_by_count":28},{"id":"2102.00582","title":"Multi-Agent Reinforcement Learning with Temporal Logic Specifications","created":"2021-02-01","cited_by_count":27},{"id":"1909.11591","title":"Modular Deep Reinforcement Learning with Temporal Logic Specifications","created":"2019-09-23","cited_by_count":25},{"id":"2010.05150","title":"Safe Reinforcement Learning with Natural Language Constraints","created":"2020-10-11","cited_by_count":23},{"id":"2202.02886","title":"Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity","created":"2022-02-06","cited_by_count":22},{"id":"2006.08767","title":"Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning","created":"2020-06-12","cited_by_count":21},{"id":"2210.09598","title":"Planning for Sample Efficient Imitation Learning","created":"2022-10-18","cited_by_count":20},{"id":"2301.12950","title":"Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs","created":"2023-01-30","cited_by_count":20},{"id":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19},{"id":"2303.02135","title":"Eventual Discounting Temporal Logic Counterfactual Experience Replay","created":"2023-03-03","cited_by_count":19},{"id":"2209.04924","title":"Meta-Reinforcement Learning via Language Instructions","created":"2022-09-11","cited_by_count":18},{"id":"1911.13152","title":"Induction of Subgoal Automata for Reinforcement Learning","created":"2019-11-29","cited_by_count":17},{"id":"2110.09461","title":"In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications","created":"2021-10-18","cited_by_count":17},{"id":"2301.08502","title":"Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning","created":"2023-01-20","cited_by_count":17},{"id":"2112.08907","title":"Inherently Explainable Reinforcement Learning in Natural Language","created":"2021-12-16","cited_by_count":16},{"id":"2112.09477","title":"Learning Reward Machines: A Study in Partially Observable Reinforcement Learning","created":"2021-12-17","cited_by_count":16},{"id":"2205.13728","title":"GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis","created":"2022-05-27","cited_by_count":16},{"id":"2107.04633","title":"Inferring Probabilistic Reward Machines from Non-Markovian Reward Processes for Reinforcement Learning","created":"2021-07-09","cited_by_count":13},{"id":"2303.17984","title":"Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning","created":"2023-03-31","cited_by_count":10},{"id":"2002.06000","title":"Extended Markov Games to Learn Multiple Tasks in Multi-Agent Reinforcement Learning","created":"2020-02-14","cited_by_count":9},{"id":"2112.08438","title":"Programmatic Reward Design by Example","created":"2021-12-14","cited_by_count":9},{"id":"2205.12532","title":"Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning","created":"2022-05-25","cited_by_count":9},{"id":"1910.09986","title":"Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning","created":"2019-10-22","cited_by_count":7},{"id":"2110.00096","title":"Decentralized Graph-Based Multi-Agent Reinforcement Learning Using Reward Machines","created":"2021-09-30","cited_by_count":7},{"id":"2208.11838","title":"Learning Task Automata for Reinforcement Learning using Hidden Markov Models","created":"2022-08-25","cited_by_count":7},{"id":"2303.05038","title":"Exploiting Contextual Structure to Generate Useful Auxiliary Tasks","created":"2023-03-09","cited_by_count":6},{"id":"2111.09475","title":"Lifelong Reinforcement Learning with Temporal Logic Formulas and Reward Machines","created":"2021-11-18","cited_by_count":5},{"id":"2008.08548","title":"A Survey of Knowledge-based Sequential Decision Making under Uncertainty","created":"2020-08-19","cited_by_count":4},{"id":"2103.06602","title":"Symbolic Reinforcement Learning for Safe RAN Control","created":"2021-03-11","cited_by_count":4},{"id":"2010.03694","title":"Learning Intrinsic Symbolic Rewards in Reinforcement Learning","created":"2020-10-08","cited_by_count":3},{"id":"2001.09066","title":"Policy Synthesis for Factored MDPs with Graph Temporal Logic Specifications","created":"2020-01-24","cited_by_count":2},{"id":"2303.14061","title":"Learning Reward Machines in Cooperative Multi-Agent Tasks","created":"2023-03-24","cited_by_count":2},{"id":"1706.01417","title":"A method for the online construction of the set of states of a Markov Decision Process using Answer Set Programming","created":"2017-06-05","cited_by_count":1}],"next_cursor":null}