{"list":"other","total":60,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"2302.08399","title":"Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks","created":"2023-02-16","cited_by_count":292},{"id":"1711.00832","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","created":"2017-11-02","cited_by_count":268},{"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":"1703.04908","title":"Emergence of Grounded Compositional Language in Multi-Agent Populations","created":"2017-03-15","cited_by_count":263},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"1702.03037","title":"Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2017-02-10","cited_by_count":209},{"id":"2211.04325","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","created":"2022-10-26","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":"1612.07182","title":"Multi-Agent Cooperation and the Emergence of (Natural) Language","created":"2016-12-21","cited_by_count":185},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"2003.04664","title":"Automatic Curriculum Learning For Deep RL: A Short Survey","created":"2020-03-10","cited_by_count":150},{"id":"1908.03963","title":"A Review of Cooperative Multi-Agent Deep Reinforcement Learning","created":"2019-08-11","cited_by_count":147},{"id":"2110.08176","title":"Collaborating with Humans without Human Data","created":"2021-10-15","cited_by_count":142},{"id":"1703.05407","title":"Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play","created":"2017-03-15","cited_by_count":141},{"id":"1705.11192","title":"Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols","created":"2017-05-31","cited_by_count":125},{"id":"1710.03748","title":"Emergent Complexity via Multi-Agent Competition","created":"2017-10-10","cited_by_count":120},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99},{"id":"1901.08106","title":"Open-ended Learning in Symmetric Zero-sum Games","created":"2019-01-23","cited_by_count":96},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87},{"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":"2012.09830","title":"Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey","created":"2020-12-17","cited_by_count":85},{"id":"2210.05359","title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","created":"2022-10-11","cited_by_count":84},{"id":"1908.06976","title":"A survey on intrinsic motivation in reinforcement learning","created":"2019-08-19","cited_by_count":81},{"id":"1803.03453","title":"The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities","created":"2018-03-09","cited_by_count":78},{"id":"2101.04882","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","created":"2021-01-13","cited_by_count":72},{"id":"2004.09468","title":"Real World Games Look Like Spinning Tops","created":"2020-04-20","cited_by_count":66},{"id":"2110.10819","title":"Shaking the foundations: delusions in sequence models for interaction and control","created":"2021-10-20","cited_by_count":62},{"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":"1707.01068","title":"Maintaining cooperation in complex social dilemmas using deep reinforcement learning","created":"2017-07-04","cited_by_count":48},{"id":"1709.02865","title":"Prosocial learning agents solve generalized Stag Hunts better than selfish ones","created":"2017-09-08","cited_by_count":47},{"id":"2010.00581","title":"Emergent Social Learning via Multi-agent Reinforcement Learning","created":"2020-10-01","cited_by_count":44},{"id":"1904.11455","title":"Ray Interference: a Source of Plateaus in Deep Reinforcement Learning","created":"2019-04-25","cited_by_count":40},{"id":"1811.05931","title":"Evolving intrinsic motivations for altruistic behavior","created":"2018-11-14","cited_by_count":30},{"id":"2102.08370","title":"Quantifying the effects of environment and population diversity in multi-agent reinforcement learning","created":"2021-02-16","cited_by_count":22},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20},{"id":"2205.06760","title":"Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning","created":"2022-05-13","cited_by_count":19},{"id":"2010.00575","title":"D3C: Reducing the Price of Anarchy in Multi-Agent Learning","created":"2020-10-01","cited_by_count":16},{"id":"1812.07019","title":"Malthusian Reinforcement Learning","created":"2018-12-17","cited_by_count":14},{"id":"2206.01134","title":"Language and Culture Internalisation for Human-Like Autotelic AI","created":"2022-06-02","cited_by_count":14},{"id":"1706.06617","title":"Observational Learning by Reinforcement Learning","created":"2017-06-20","cited_by_count":12},{"id":"2206.05060","title":"Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENS","created":"2022-06-10","cited_by_count":10},{"id":"2012.08564","title":"Grounding Artificial Intelligence in the Origins of Human Behavior","created":"2020-12-15","cited_by_count":3},{"id":"2302.01180","title":"Diversity Through Exclusion (DTE): Niche Identification for Reinforcement Learning through Value-Decomposition","created":"2023-02-02","cited_by_count":2}],"next_cursor":null}