{"list":"other","total":70,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"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":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1606.02647","title":"Safe and Efficient Off-Policy Reinforcement Learning","created":"2016-06-08","cited_by_count":264},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"id":"1809.02627","title":"Unity: A General Platform for Intelligent Agents","created":"2018-09-07","cited_by_count":236},{"id":"1802.07740","title":"Machine Theory of Mind","created":"2018-02-21","cited_by_count":226},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"2003.02979","title":"\"Other-Play\" for Zero-Shot Coordination","created":"2020-03-06","cited_by_count":198},{"id":"1902.00506","title":"The Hanabi Challenge: A New Frontier for AI Research","created":"2019-02-01","cited_by_count":197},{"id":"2002.06177","title":"The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence","created":"2020-02-14","cited_by_count":195},{"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":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"2110.08176","title":"Collaborating with Humans without Human Data","created":"2021-10-15","cited_by_count":142},{"id":"1802.07245","title":"Meta-Reinforcement Learning of Structured Exploration Strategies","created":"2018-02-20","cited_by_count":130},{"id":"2002.00632","title":"Effective Diversity in Population Based Reinforcement Learning","created":"2020-02-03","cited_by_count":119},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111},{"id":"1804.00168","title":"Learning to Navigate in Cities Without a Map","created":"2018-03-31","cited_by_count":104},{"id":"1805.07914","title":"Imitating Latent Policies from Observation","created":"2018-05-21","cited_by_count":101},{"id":"1905.13566","title":"Recent Advances in Imitation Learning from Observation","created":"2019-05-30","cited_by_count":93},{"id":"2008.06043","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","created":"2020-08-13","cited_by_count":93},{"id":"1905.10985","title":"AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence","created":"2019-05-27","cited_by_count":86},{"id":"1806.10729","title":"Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation","created":"2018-06-28","cited_by_count":81},{"id":"1612.07307","title":"Loss is its own Reward: Self-Supervision for Reinforcement Learning","created":"2016-12-21","cited_by_count":72},{"id":"1905.03030","title":"Meta-learning of Sequential Strategies","created":"2019-05-08","cited_by_count":70},{"id":"1802.04564","title":"Diversity-Driven Exploration Strategy for Deep Reinforcement Learning","created":"2018-02-13","cited_by_count":65},{"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":"2008.02790","title":"Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices","created":"2020-08-06","cited_by_count":59},{"id":"2002.02325","title":"Social diversity and social preferences in mixed-motive reinforcement learning","created":"2020-02-06","cited_by_count":49},{"id":"1904.13310","title":"Survey of Dropout Methods for Deep Neural Networks","created":"2019-04-25","cited_by_count":44},{"id":"2010.11223","title":"Meta-trained agents implement Bayes-optimal agents","created":"2020-10-21","cited_by_count":38},{"id":"2107.05697","title":"Few-shot Language Coordination by Modeling Theory of Mind","created":"2021-07-12","cited_by_count":32},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31},{"id":"2011.04764","title":"Deep Reinforcement Learning for Navigation in AAA Video Games","created":"2020-11-09","cited_by_count":27},{"id":"2102.04736","title":"Reverb: A Framework For Experience Replay","created":"2021-02-09","cited_by_count":27},{"id":"2012.05874","title":"Hindsight and Sequential Rationality of Correlated Play","created":"2020-12-10","cited_by_count":22},{"id":"1906.10187","title":"Learning to Interactively Learn and Assist","created":"2019-06-24","cited_by_count":20},{"id":"2104.13424","title":"Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution","created":"2021-04-27","cited_by_count":20},{"id":"2103.08067","title":"Quasi-Equivalence Discovery for Zero-Shot Emergent Communication","created":"2021-03-14","cited_by_count":19},{"id":"1806.02308","title":"Model-free, Model-based, and General Intelligence","created":"2018-06-06","cited_by_count":14},{"id":"2106.04516","title":"Launchpad: A Programming Model for Distributed Machine Learning Research","created":"2021-06-07","cited_by_count":14},{"id":"2011.09294","title":"Using Unity to Help Solve Intelligence","created":"2020-11-18","cited_by_count":13},{"id":"1706.06617","title":"Observational Learning by Reinforcement Learning","created":"2017-06-20","cited_by_count":12},{"id":"2106.09086","title":"Learned Belief Search: Efficiently Improving Policies in Partially Observable Settings","created":"2021-06-16","cited_by_count":10},{"id":"1906.01470","title":"Options as responses: Grounding behavioural hierarchies in multi-agent RL","created":"2019-06-04","cited_by_count":7},{"id":"2011.06335","title":"Hierarchical reinforcement learning for efficient exploration and transfer","created":"2020-11-12","cited_by_count":5},{"id":"2106.11754","title":"Experiments in Artificial Culture: from noisy imitation to storytelling robots","created":"2021-06-22","cited_by_count":1}],"next_cursor":null}