{"list":"other","total":59,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"2206.14576","title":"Using cognitive psychology to understand GPT-3","created":"2022-06-21","cited_by_count":398},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"1709.04326","title":"Learning with Opponent-Learning Awareness","created":"2017-09-13","cited_by_count":222},{"id":"2303.10130","title":"GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models","created":"2023-03-17","cited_by_count":176},{"id":"2212.03551","title":"Talking About Large Language Models","created":"2022-12-07","cited_by_count":175},{"id":"2012.08630","title":"Open Problems in Cooperative AI","created":"2020-12-15","cited_by_count":168},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166},{"id":"2212.05206","title":"Thinking Fast and Slow in Large Language Models","created":"2022-12-10","cited_by_count":137},{"id":"1709.08071","title":"Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems","created":"2017-09-23","cited_by_count":131},{"id":"1709.08568","title":"The Consciousness Prior","created":"2017-09-25","cited_by_count":107},{"id":"1609.05559","title":"Opponent Modeling in Deep Reinforcement Learning","created":"2016-09-18","cited_by_count":97},{"id":"1703.10069","title":"Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games","created":"2017-03-29","cited_by_count":96},{"id":"1801.10408","title":"'It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisions","created":"2018-01-31","cited_by_count":91},{"id":"2112.14168","title":"A Survey on Gender Bias in Natural Language Processing","created":"2021-12-28","cited_by_count":89},{"id":"1902.11097","title":"Predictive Inequity in Object Detection","created":"2019-02-21","cited_by_count":77},{"id":"2003.10014","title":"Reinforcement Learning in Economics and Finance","created":"2020-03-22","cited_by_count":58},{"id":"1811.08469","title":"Stable Opponent Shaping in Differentiable Games","created":"2018-11-20","cited_by_count":49},{"id":"1512.05832","title":"Learning the Preferences of Ignorant, Inconsistent Agents","created":"2015-12-18","cited_by_count":45},{"id":"1712.05812","title":"Occam's razor is insufficient to infer the preferences of irrational agents","created":"2017-12-15","cited_by_count":45},{"id":"2205.01447","title":"Model-Free Opponent Shaping","created":"2022-05-03","cited_by_count":44},{"id":"2011.00382","title":"A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning","created":"2020-10-31","cited_by_count":41},{"id":"2210.15303","title":"Can language models handle recursively nested grammatical structures? A case study on comparing models and humans","created":"2022-10-27","cited_by_count":41},{"id":"2001.04377","title":"When Humans Aren't Optimal: Robots that Collaborate with Risk-Aware Humans","created":"2020-01-13","cited_by_count":34},{"id":"2204.10759","title":"The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models","created":"2022-04-22","cited_by_count":31},{"id":"2102.00582","title":"Multi-Agent Reinforcement Learning with Temporal Logic Specifications","created":"2021-02-01","cited_by_count":27},{"id":"2212.03201","title":"Misspecification in Inverse Reinforcement Learning","created":"2022-12-06","cited_by_count":27},{"id":"2208.10687","title":"The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types","created":"2022-08-23","cited_by_count":26},{"id":"2111.06956","title":"Human irrationality: both bad and good for reward inference","created":"2021-11-12","cited_by_count":25},{"id":"1901.09216","title":"Modelling Bounded Rationality in Multi-Agent Interactions by Generalized Recursive Reasoning","created":"2019-01-26","cited_by_count":24},{"id":"1906.11064","title":"Reasoning about Hypothetical Agent Behaviours and their Parameters","created":"2019-06-26","cited_by_count":24},{"id":"1712.05441","title":"A Game-Theoretic Taxonomy and Survey of Defensive Deception for Cybersecurity and Privacy","created":"2017-12-14","cited_by_count":22},{"id":"1304.2759","title":"Reasoning About Beliefs and Actions Under Computational Resource Constraints","created":"2013-03-27","cited_by_count":18},{"id":"2002.05502","title":"Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic","created":"2020-02-13","cited_by_count":12},{"id":"1709.09839","title":"Heuristic Online Goal Recognition in Continuous Domains","created":"2017-09-28","cited_by_count":11},{"id":"1905.11759","title":"Manipulating a Learning Defender and Ways to Counteract","created":"2019-05-28","cited_by_count":8},{"id":"2012.08485","title":"Indecision Modeling","created":"2020-12-15","cited_by_count":8},{"id":"2109.14039","title":"Marked Attribute Bias in Natural Language Inference","created":"2021-09-28","cited_by_count":6},{"id":"2105.12856","title":"Beyond Algorithmic Bias: A Socio-Computational Interrogation of the Google Search by Image Algorithm","created":"2021-05-26","cited_by_count":5},{"id":"2210.01122","title":"BIASeD: Bringing Irrationality into Automated System Design","created":"2022-10-01","cited_by_count":5},{"id":"1709.03339","title":"Autonomous Quadrotor Landing using Deep Reinforcement Learning","created":"2017-09-11","cited_by_count":4},{"id":"2202.13985","title":"The dangers in algorithms learning humans' values and irrationalities","created":"2022-02-28","cited_by_count":3},{"id":"2208.03209","title":"Bias and Fairness in Computer Vision Applications of the Criminal Justice System","created":"2022-08-05","cited_by_count":3},{"id":"2002.08891","title":"Deep Neural Networks Carve the Brain at its Joints","created":"2020-02-20","cited_by_count":2},{"id":"2109.04744","title":"Automated Machine Learning, Bounded Rationality, and Rational Metareasoning","created":"2021-09-10","cited_by_count":2},{"id":"2201.04266","title":"Safe Equilibrium","created":"2022-01-12","cited_by_count":2},{"id":"1511.05662","title":"Discovering Underlying Plans Based on Distributed Representations of Actions","created":"2015-11-18","cited_by_count":1},{"id":"1808.04600","title":"Reconciling Irrational Human Behavior with AI based Decision Making: A Quantum Probabilistic Approach","created":"2018-08-14","cited_by_count":1},{"id":"2006.04072","title":"Implications of Human Irrationality for Reinforcement Learning","created":"2020-06-07","cited_by_count":1},{"id":"2106.07100","title":"The Impact of Irrational Behaviours in the Optional Prisoner's Dilemma with Game-Environment Feedback","created":"2021-06-13","cited_by_count":1},{"id":"2107.09119","title":"Rational Verification for Probabilistic Systems","created":"2021-07-19","cited_by_count":1}],"next_cursor":null}