{"list":"other","total":67,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"2003.04960","title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","created":"2020-03-10","cited_by_count":373},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1711.00832","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","created":"2017-11-02","cited_by_count":268},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"1704.03003","title":"Automated Curriculum Learning for Neural Networks","created":"2017-04-10","cited_by_count":257},{"id":"2009.14471","title":"PettingZoo: Gym for Multi-Agent Reinforcement Learning","created":"2020-09-30","cited_by_count":220},{"id":"1907.13440","title":"MineRL: A Large-Scale Dataset of Minecraft Demonstrations","created":"2019-07-29","cited_by_count":215},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"1901.01753","title":"Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions","created":"2019-01-07","cited_by_count":192},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"1603.01121","title":"Deep Reinforcement Learning from Self-Play in Imperfect-Information Games","created":"2016-03-03","cited_by_count":158},{"id":"2003.04664","title":"Automatic Curriculum Learning For Deep RL: A Short Survey","created":"2020-03-10","cited_by_count":150},{"id":"1703.05407","title":"Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play","created":"2017-03-15","cited_by_count":141},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138},{"id":"2009.04416","title":"Phasic Policy Gradient","created":"2020-09-09","cited_by_count":123},{"id":"1910.07224","title":"Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments","created":"2019-10-16","cited_by_count":119},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111},{"id":"2003.08536","title":"Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions","created":"2020-03-19","cited_by_count":106},{"id":"2006.11751","title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","created":"2020-06-21","cited_by_count":93},{"id":"1812.03381","title":"Learning Montezuma's Revenge from a Single Demonstration","created":"2018-12-08","cited_by_count":80},{"id":"2405.15568","title":"OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code","created":"2024-05-24","cited_by_count":74},{"id":"2101.04882","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","created":"2021-01-13","cited_by_count":72},{"id":"2306.01711","title":"OMNI: Open-endedness via Models of human Notions of Interestingness","created":"2023-06-02","cited_by_count":70},{"id":"1903.00742","title":"Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research","created":"2019-03-02","cited_by_count":61},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51},{"id":"1903.00784","title":"Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents","created":"2019-03-02","cited_by_count":44},{"id":"1910.03552","title":"TorchBeast: A PyTorch Platform for Distributed RL","created":"2019-10-08","cited_by_count":41},{"id":"2109.11052","title":"On Bonus-Based Exploration Methods in the Arcade Learning Environment","created":"2021-09-22","cited_by_count":37},{"id":"2106.14876","title":"Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft","created":"2021-06-28","cited_by_count":35},{"id":"2011.06363","title":"Griddly: A platform for AI research in games","created":"2020-11-12","cited_by_count":31},{"id":"2303.03376","title":"MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning","created":"2023-03-06","cited_by_count":31},{"id":"2305.12487","title":"Augmenting Autotelic Agents with Large Language Models","created":"2023-05-21","cited_by_count":30},{"id":"1909.12892","title":"Automated curricula through setter-solver interactions","created":"2019-09-27","cited_by_count":26},{"id":"2408.01072","title":"A Survey on Self-play Methods in Reinforcement Learning","created":"2024-08-02","cited_by_count":26},{"id":"2406.12905","title":"PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice","created":"2024-06-11","cited_by_count":24},{"id":"2203.11889","title":"Insights From the NeurIPS 2021 NetHack Challenge","created":"2022-03-22","cited_by_count":20},{"id":"2304.12877","title":"Proximal Curriculum for Reinforcement Learning Agents","created":"2023-04-25","cited_by_count":20},{"id":"2103.09815","title":"TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL","created":"2021-03-17","cited_by_count":18},{"id":"2308.10797","title":"Stabilizing Unsupervised Environment Design with a Learned Adversary","created":"2023-08-21","cited_by_count":17},{"id":"2211.00539","title":"Dungeons and Data: A Large-Scale NetHack Dataset","created":"2022-11-01","cited_by_count":16},{"id":"2310.02782","title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design","created":"2023-10-04","cited_by_count":16},{"id":"2202.10608","title":"It Takes Four to Tango: Multiagent Selfplay for Automatic Curriculum Generation","created":"2022-02-22","cited_by_count":14},{"id":"2305.19240","title":"NetHack is Hard to Hack","created":"2023-05-30","cited_by_count":11},{"id":"2403.13091","title":"JaxUED: A simple and useable UED library in Jax","created":"2024-03-19","cited_by_count":11},{"id":"2311.03736","title":"Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning","created":"2023-11-07","cited_by_count":9},{"id":"2204.13250","title":"Watts: Infrastructure for Open-Ended Learning","created":"2022-04-28","cited_by_count":2}],"next_cursor":null}