{"list":"other","total":52,"rows":[{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"id":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"id":"1808.04355","title":"Large-Scale Study of Curiosity-Driven Learning","created":"2018-08-13","cited_by_count":280},{"id":"1906.00695","title":"Continual learning with hypernetworks","created":"2019-06-03","cited_by_count":273},{"id":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1907.11180","title":"Google Research Football: A Novel Reinforcement Learning Environment","created":"2019-07-25","cited_by_count":260},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"1802.10269","title":"Selective Experience Replay for Lifelong Learning","created":"2018-02-28","cited_by_count":241},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"1901.10995","title":"Go-Explore: a New Approach for Hard-Exploration Problems","created":"2019-01-30","cited_by_count":212},{"id":"2002.06038","title":"Never Give Up: Learning Directed Exploration Strategies","created":"2020-02-14","cited_by_count":212},{"id":"1902.00506","title":"The Hanabi Challenge: A New Frontier for AI Research","created":"2019-02-01","cited_by_count":197},{"id":"1910.07483","title":"MAVEN: Multi-Agent Variational Exploration","created":"2019-10-16","cited_by_count":185},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"2003.08039","title":"ROMA: Multi-Agent Reinforcement Learning with Emergent Roles","created":"2020-03-18","cited_by_count":137},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"id":"2010.01523","title":"RODE: Learning Roles to Decompose Multi-Agent Tasks","created":"2020-10-04","cited_by_count":125},{"id":"1807.11622","title":"Count-Based Exploration with the Successor Representation","created":"2018-07-31","cited_by_count":112},{"id":"2106.02195","title":"Celebrating Diversity in Shared Multi-Agent Reinforcement Learning","created":"2021-06-04","cited_by_count":98},{"id":"1911.01417","title":"Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards","created":"2019-11-04","cited_by_count":78},{"id":"1910.05512","title":"Influence-Based Multi-Agent Exploration","created":"2019-10-12","cited_by_count":75},{"id":"2010.01856","title":"My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control","created":"2020-10-05","cited_by_count":70},{"id":"1811.01458","title":"Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning","created":"2018-11-04","cited_by_count":68},{"id":"2107.11444","title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","created":"2021-07-23","cited_by_count":57},{"id":"1706.08090","title":"Count-Based Exploration in Feature Space for Reinforcement Learning","created":"2017-06-25","cited_by_count":49},{"id":"2111.11032","title":"Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration","created":"2021-11-22","cited_by_count":49},{"id":"1602.04951","title":"Q($\\lambda$) with Off-Policy Corrections","created":"2016-02-16","cited_by_count":48},{"id":"2010.00581","title":"Emergent Social Learning via Multi-agent Reinforcement Learning","created":"2020-10-01","cited_by_count":44},{"id":"2007.03669","title":"See, Hear, Explore: Curiosity via Audio-Visual Association","created":"2020-07-07","cited_by_count":43},{"id":"2010.02974","title":"UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning","created":"2020-10-06","cited_by_count":33},{"id":"2007.07011","title":"Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting","created":"2020-07-14","cited_by_count":29},{"id":"2202.10203","title":"Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning","created":"2022-02-21","cited_by_count":29},{"id":"2010.01062","title":"Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning","created":"2020-10-02","cited_by_count":28},{"id":"2006.05842","title":"The Emergence of Individuality","created":"2020-06-10","cited_by_count":22},{"id":"1911.04094","title":"SMIX($\\lambda$): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning","created":"2019-11-11","cited_by_count":15},{"id":"2106.07039","title":"Contingency-Aware Influence Maximization: A Reinforcement Learning Approach","created":"2021-06-13","cited_by_count":13},{"id":"1909.10651","title":"Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization","created":"2019-09-23","cited_by_count":12}],"next_cursor":null}