{"list":"other","total":79,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"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":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"1504.04909","title":"Illuminating search spaces by mapping elites","created":"2015-04-20","cited_by_count":425},{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"1611.07507","title":"Variational Intrinsic Control","created":"2016-11-22","cited_by_count":267},{"id":"2201.13259","title":"Trajectory balance: Improved credit assignment in GFlowNets","created":"2022-01-31","cited_by_count":251},{"id":"2009.14471","title":"PettingZoo: Gym for Multi-Agent Reinforcement Learning","created":"2020-09-30","cited_by_count":220},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"id":"1407.3501","title":"Robots that can adapt like animals","created":"2014-07-13","cited_by_count":204},{"id":"2203.04115","title":"Biological Sequence Design with GFlowNets","created":"2022-03-02","cited_by_count":174},{"id":"1512.07679","title":"Deep Reinforcement Learning in Large Discrete Action Spaces","created":"2015-12-24","cited_by_count":161},{"id":"2002.00632","title":"Effective Diversity in Population Based Reinforcement Learning","created":"2020-02-03","cited_by_count":119},{"id":"2202.01361","title":"Generative Flow Networks for Discrete Probabilistic Modeling","created":"2022-02-03","cited_by_count":114},{"id":"1712.06560","title":"Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents","created":"2017-12-18","cited_by_count":107},{"id":"1811.11711","title":"Neural probabilistic motor primitives for humanoid control","created":"2018-11-28","cited_by_count":97},{"id":"1711.08946","title":"Action Branching Architectures for Deep Reinforcement Learning","created":"2017-11-24","cited_by_count":92},{"id":"1511.04636","title":"Deep Reinforcement Learning with a Natural Language Action Space","created":"2015-11-14","cited_by_count":88},{"id":"1905.04722","title":"Learning Phase Competition for Traffic Signal Control","created":"2019-05-12","cited_by_count":87},{"id":"1707.02747","title":"Robust Imitation of Diverse Behaviors","created":"2017-07-10","cited_by_count":86},{"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":"1911.04936","title":"Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning","created":"2019-11-12","cited_by_count":78},{"id":"1809.02121","title":"Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning","created":"2018-09-06","cited_by_count":77},{"id":"1902.00183","title":"Learning Action Representations for Reinforcement Learning","created":"2019-02-01","cited_by_count":75},{"id":"1712.00600","title":"MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence","created":"2017-12-02","cited_by_count":71},{"id":"1511.04143","title":"Deep Reinforcement Learning in Parameterized Action Space","created":"2015-11-13","cited_by_count":68},{"id":"1907.08225","title":"Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery","created":"2019-07-18","cited_by_count":68},{"id":"1802.04564","title":"Diversity-Driven Exploration Strategy for Deep Reinforcement Learning","created":"2018-02-13","cited_by_count":65},{"id":"1509.01644","title":"Reinforcement Learning with Parameterized Actions","created":"2015-09-05","cited_by_count":63},{"id":"2010.12001","title":"Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing","created":"2020-10-22","cited_by_count":61},{"id":"1810.06394","title":"Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space","created":"2018-10-10","cited_by_count":58},{"id":"1902.07151","title":"Emergent Coordination Through Competition","created":"2019-02-19","cited_by_count":57},{"id":"1903.01344","title":"Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space","created":"2019-03-04","cited_by_count":54},{"id":"1705.05035","title":"Discrete Sequential Prediction of Continuous Actions for Deep RL","created":"2017-05-14","cited_by_count":51},{"id":"1912.03905","title":"ChainerRL: A Deep Reinforcement Learning Library","created":"2019-12-09","cited_by_count":51},{"id":"1810.01266","title":"Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information","created":"2018-09-29","cited_by_count":41},{"id":"1912.11077","title":"Discrete and Continuous Action Representation for Practical RL in Video Games","created":"2019-12-23","cited_by_count":39},{"id":"2103.07927","title":"Modelling Behavioural Diversity for Learning in Open-Ended Games","created":"2021-03-14","cited_by_count":39},{"id":"1905.00976","title":"Collaborative Evolutionary Reinforcement Learning","created":"2019-05-02","cited_by_count":37},{"id":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37},{"id":"2006.01482","title":"Multi-Agent Determinantal Q-Learning","created":"2020-06-02","cited_by_count":36},{"id":"2103.04564","title":"Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization","created":"2021-03-08","cited_by_count":35},{"id":"1906.00088","title":"Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies","created":"2019-05-31","cited_by_count":34},{"id":"2004.12974","title":"Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning","created":"2020-04-27","cited_by_count":31},{"id":"1811.05869","title":"Large-scale Interactive Recommendation with Tree-structured Policy Gradient","created":"2018-11-14","cited_by_count":30},{"id":"1906.10667","title":"Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives","created":"2019-06-25","cited_by_count":30},{"id":"1805.10309","title":"Learning Self-Imitating Diverse Policies","created":"2018-05-25","cited_by_count":29},{"id":"1906.12266","title":"Growing Action Spaces","created":"2019-06-28","cited_by_count":29},{"id":"1902.01119","title":"The Natural Language of Actions","created":"2019-02-04","cited_by_count":28},{"id":"2106.00136","title":"Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning","created":"2021-05-31","cited_by_count":25},{"id":"1905.04388","title":"Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces","created":"2019-05-10","cited_by_count":24},{"id":"2204.02246","title":"Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization","created":"2022-04-04","cited_by_count":23},{"id":"1812.02609","title":"A Framework for Adaptive MCMC Targeting Multimodal Distributions","created":"2018-12-06","cited_by_count":21},{"id":"2102.04323","title":"Discovering a set of policies for the worst case reward","created":"2021-02-08","cited_by_count":21},{"id":"1905.05252","title":"Learning Novel Policies For Tasks","created":"2019-05-13","cited_by_count":20},{"id":"2109.08522","title":"Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoires","created":"2021-09-16","cited_by_count":20},{"id":"1903.04959","title":"Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces","created":"2019-03-12","cited_by_count":16},{"id":"1810.09656","title":"Hierarchical Approaches for Reinforcement Learning in Parameterized Action Space","created":"2018-10-23","cited_by_count":15},{"id":"1906.07315","title":"Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination","created":"2019-06-18","cited_by_count":14},{"id":"2112.15025","title":"Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates","created":"2021-12-30","cited_by_count":14},{"id":"2006.07781","title":"Non-local Policy Optimization via Diversity-regularized Collaborative Exploration","created":"2020-06-14","cited_by_count":13},{"id":"2107.07506","title":"Adaptable Agent Populations via a Generative Model of Policies","created":"2021-07-15","cited_by_count":12},{"id":"2005.10696","title":"Novel Policy Seeking with Constrained Optimization","created":"2020-05-21","cited_by_count":11},{"id":"2011.11995","title":"InTAS -- The Ingolstadt Traffic Scenario for SUMO","created":"2020-11-24","cited_by_count":11},{"id":"2103.13462","title":"Why Do Local Methods Solve Nonconvex Problems?","created":"2021-03-24","cited_by_count":8},{"id":"2011.02614","title":"Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity","created":"2020-11-05","cited_by_count":7},{"id":"2110.14538","title":"Reinforcement Learning in Factored Action Spaces using Tensor Decompositions","created":"2021-10-27","cited_by_count":6},{"id":"1902.10140","title":"Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies","created":"2019-02-26","cited_by_count":5}],"next_cursor":null}