{"version":1,"pages":[{"id":"-LKHJDzyEohugWnNMPL1","title":"The AGI Landscape","pathname":"/","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LjBVuMsrRa_Duk8cULO","title":"我们的愿景 Our vision","pathname":"/intro","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LSQNCXLdLOYOKaktExo","title":"Papers","pathname":"/papers-1","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoZFtLdV2_6fcQN5FK","title":"Rationality and intelligence","pathname":"/rationality-and-intelligence","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoZ14W1YlpRExNlvGA","title":"AI safety gridworlds","pathname":"/ai-safety-gridworlds","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoXzI6Jvzni7P0HK_E","title":"Modeling Friends and Foes","pathname":"/modeling-friends-and-foes","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LKHM7vwHF0RW_dFSTu0","title":"Forget-me-not-Process","pathname":"/forget-me-not-process","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LKHM7wDmjBTFAe_yuoC","title":"Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study","pathname":"/cognitive_psychology_dnn","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LKMbZsthep8fUoezC-2","title":"Universal Transformers","pathname":"/universal-transformers","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LKX1IaAsO7Vfh2ZYPdg","title":"Graph Convolutional Policy Network","pathname":"/graph-convolutional-policy-network","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoZJxLQZXnqWMq1i9t","title":"Thermodynamics as a theory of decision-making with informationprocessing costs","pathname":"/thermodynamics-as-a-theory-of-decision-making-with-informationprocessing-costs","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoZX4merbVU8noFS1O","title":"Concrete Problems in AI Safety","pathname":"/concrete-problems-in-ai-safety","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLocAAfe7O8XYHDKgys","title":"A course in game theory","pathname":"/a-course-in-game-theory","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoecyupMtf-gDSp3Ci","title":"Theory of games and economic behavior","pathname":"/theory-of-games-and-economic-behavior","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoed_470XZ0cvHq03t","title":"Reinforcement learning: An introduction 1e","pathname":"/untitled-1","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoyOC7ipO8k7DsXRwV","title":"Regret analysis of stochastic and nonstochastic multi-armed bandit problems","pathname":"/regret-analysis-of-stochastic-and-nonstochastic-multi-armed-bandit-problems","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoyTcJIgGi55v345He","title":"The nonstochastic multiarmed bandit problem","pathname":"/the-nonstochastic-multiarmed-bandit-problem","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoyXe9UwORYrjPBm7o","title":"Information theory of decisions and actions","pathname":"/information-theory-of-decisions-and-actions","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoydK88HbE14mdhiNQ","title":"Clustering with bregman divergences","pathname":"/clustering-with-bregman-divergences","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoyh_-T7F9KNaQ0jPl","title":"Quantal Response Equilibria for Normal Form Games","pathname":"/quantal-response-equilibria-for-normal-form-games","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoymDHarQzC76Ub9FQ","title":"The numerics of gans","pathname":"/the-numerics-of-gans","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoyqCUn6XvAu1WnfUe","title":"The Mechanics of n-Player Differentiable Games","pathname":"/the-mechanics-of-n-player-differentiable-games","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoytklvb-xBDIesObG","title":"Reactive bandits with attitude","pathname":"/reactive-bandits-with-attitude","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoyz1yf7JbHLd5QYZ2","title":"Data clustering by markovian relaxation and the information bottleneck method","pathname":"/data-clustering-by-markovian-relaxation-and-the-information-bottleneck-method","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoz2bba_2lsJMkNVZC","title":"Information bottleneck for Gaussian variables","pathname":"/information-bottleneck-for-gaussian-variables","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLoz8CC8g-Q11JODaYb","title":"Bounded Rationality, Abstraction, and Hierarchical Decision-Making: An Information-Theoretic Optimal","pathname":"/bounded-rationality-abstraction-and-hierarchical-decision-making-an-information-theoretic-optimal","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLozDdyQ3zT4Ya56k5V","title":"Risk sensitive path integral control","pathname":"/risk-sensitive-path-integral-control","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLozMLhCrzFakgK7iFm","title":"Information, utility and bounded rationality","pathname":"/information-utility-and-bounded-rationality","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLozTgCHk7brRoAZGoX","title":"Hysteresis effects of changing the parameters of noncooperative games","pathname":"/hysteresis-effects-of-changing-the-parameters-of-noncooperative-games","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLozcLzCGLKk5ouJpBN","title":"The best of both worlds: stochastic and adversarial bandits","pathname":"/the-best-of-both-worlds-stochastic-and-adversarial-bandits","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLozhfYYmDS-ZljZ9LA","title":"One practical algorithm for both stochastic and adversarial bandits","pathname":"/one-practical-algorithm-for-both-stochastic-and-adversarial-bandits","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLozlqM0qaFpIRXIrZf","title":"An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits","pathname":"/an-algorithm-with-nearly-optimal-pseudo-regret-for-both-stochastic-and-adversarial-bandits","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLozpF5XZeWlSqgGMTX","title":"Friend-or-Foe Q-Learning in General-Sum Games","pathname":"/friend-or-foe-q-learning-in-general-sum-games","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLozuKYRolRh1CHpB20","title":"New criteria and a new algorithm for learning in multi-agent systems","pathname":"/new-criteria-and-a-new-algorithm-for-learning-in-multi-agent-systems","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLozzIromWokXM0N9rg","title":"Correlated Q-Learning","pathname":"/correlated-q-learning","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLp-2YtkH4LkQnsA3uQ","title":"Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning","pathname":"/learning-to-compete-coordinate-and-cooperate-in-repeated-games-using-reinforcement-learning","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLp-7pHuJqFFcV47wt7","title":"Learning against sequential opponents in repeated stochastic games","pathname":"/learning-against-sequential-opponents-in-repeated-stochastic-games","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLp-B9tXBxV07pMFbOj","title":"On the likelihood that one unknown probability exceeds another in view of the evidence of two sample","pathname":"/on-the-likelihood-that-one-unknown-probability-exceeds-another-in-view-of-the-evidence-of-two-sample","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLp-Eu6R80R0CmRynSl","title":"An empirical evaluation of Thompson Sampling","pathname":"/an-empirical-evaluation-of-thompson-sampling","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLp-Ipd_XsQ9yljFGvN","title":"What game are we playing? end-to-end learning in normal and extensive form games","pathname":"/what-game-are-we-playing-end-to-end-learning-in-normal-and-extensive-form-games","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LLp-O69U5NH65aOJG6k","title":"Intriguing properties of neural networks","pathname":"/intriguing-properties-of-neural-networks","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LSQLlQSYKKNA-nJRlxc","title":"Untitled","pathname":"/intriguing-properties-of-neural-networks/untitled","siteSpaceId":"sitesp_LOyPe","description":"","breadcrumbs":[{"label":"Intriguing properties of neural networks"}]},{"id":"-LLp-RmkNgiOwNsoaoDP","title":"Explaining and harnessing adversarial examples","pathname":"/explaining-and-harnessing-adversarial-examples","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-Lfy_kd0avq_smFcuGvn","title":"The Landscape of Deep Reinforcement Learning","pathname":"/the-landscape-of-deep-reinforcement-learning","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LiGz00049Hhe9RmujmK","title":"用因果影响图建模通用人工智能安全框架","pathname":"/yong-yin-guo-ying-xiang-tu-jian-mo-tong-yong-ren-gong-zhi-neng-an-quan-kuang-jia","siteSpaceId":"sitesp_LOyPe","description":""},{"id":"-LSQLyOSwIRBZ6LoH1qe","title":"test","pathname":"/papers/test","siteSpaceId":"sitesp_LOyPe","description":"","breadcrumbs":[{"label":"Papers"}]},{"id":"-LSQLq9a6kKeEtv34d4q","title":"Measuring and avoiding side effects using relative reachability","pathname":"/papers/papers","siteSpaceId":"sitesp_LOyPe","description":"","breadcrumbs":[{"label":"Papers"}]}]}