# AGI University

## AGI University

- [The AGI Landscape](https://agi.university/master.md)
- [我们的愿景 Our vision](https://agi.university/intro.md)
- [Papers](https://agi.university/papers-1.md)
- [Rationality and intelligence](https://agi.university/rationality-and-intelligence.md)
- [AI safety gridworlds](https://agi.university/ai-safety-gridworlds.md)
- [Modeling Friends and Foes](https://agi.university/modeling-friends-and-foes.md)
- [Forget-me-not-Process](https://agi.university/forget-me-not-process.md)
- [Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study](https://agi.university/cognitive_psychology_dnn.md)
- [Universal Transformers](https://agi.university/universal-transformers.md)
- [Graph Convolutional Policy Network](https://agi.university/graph-convolutional-policy-network.md)
- [Thermodynamics as a theory of decision-making with informationprocessing costs](https://agi.university/thermodynamics-as-a-theory-of-decision-making-with-informationprocessing-costs.md)
- [Concrete Problems in AI Safety](https://agi.university/concrete-problems-in-ai-safety.md)
- [A course in game theory](https://agi.university/a-course-in-game-theory.md)
- [Theory of games and economic behavior](https://agi.university/theory-of-games-and-economic-behavior.md)
- [Reinforcement learning: An introduction 1e](https://agi.university/untitled-1.md)
- [Regret analysis of stochastic and nonstochastic multi-armed bandit problems](https://agi.university/regret-analysis-of-stochastic-and-nonstochastic-multi-armed-bandit-problems.md)
- [The nonstochastic multiarmed bandit problem](https://agi.university/the-nonstochastic-multiarmed-bandit-problem.md)
- [Information theory of decisions and actions](https://agi.university/information-theory-of-decisions-and-actions.md)
- [Clustering with bregman divergences](https://agi.university/clustering-with-bregman-divergences.md)
- [Quantal Response Equilibria for Normal Form Games](https://agi.university/quantal-response-equilibria-for-normal-form-games.md)
- [The numerics of gans](https://agi.university/the-numerics-of-gans.md)
- [The Mechanics of n-Player Differentiable Games](https://agi.university/the-mechanics-of-n-player-differentiable-games.md)
- [Reactive bandits with attitude](https://agi.university/reactive-bandits-with-attitude.md)
- [Data clustering by markovian relaxation and the information bottleneck method](https://agi.university/data-clustering-by-markovian-relaxation-and-the-information-bottleneck-method.md)
- [Information bottleneck for Gaussian variables](https://agi.university/information-bottleneck-for-gaussian-variables.md)
- [Bounded Rationality, Abstraction, and Hierarchical Decision-Making: An Information-Theoretic Optimal](https://agi.university/bounded-rationality-abstraction-and-hierarchical-decision-making-an-information-theoretic-optimal.md)
- [Risk sensitive path integral control](https://agi.university/risk-sensitive-path-integral-control.md)
- [Information, utility and bounded rationality](https://agi.university/information-utility-and-bounded-rationality.md)
- [Hysteresis effects of changing the parameters of noncooperative games](https://agi.university/hysteresis-effects-of-changing-the-parameters-of-noncooperative-games.md)
- [The best of both worlds: stochastic and adversarial bandits](https://agi.university/the-best-of-both-worlds-stochastic-and-adversarial-bandits.md)
- [One practical algorithm for both stochastic and adversarial bandits](https://agi.university/one-practical-algorithm-for-both-stochastic-and-adversarial-bandits.md)
- [An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits](https://agi.university/an-algorithm-with-nearly-optimal-pseudo-regret-for-both-stochastic-and-adversarial-bandits.md)
- [Friend-or-Foe Q-Learning in General-Sum Games](https://agi.university/friend-or-foe-q-learning-in-general-sum-games.md)
- [New criteria and a new algorithm for learning in multi-agent systems](https://agi.university/new-criteria-and-a-new-algorithm-for-learning-in-multi-agent-systems.md)
- [Correlated Q-Learning](https://agi.university/correlated-q-learning.md)
- [Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning](https://agi.university/learning-to-compete-coordinate-and-cooperate-in-repeated-games-using-reinforcement-learning.md)
- [Learning against sequential opponents in repeated stochastic games](https://agi.university/learning-against-sequential-opponents-in-repeated-stochastic-games.md)
- [On the likelihood that one unknown probability exceeds another in view of the evidence of two sample](https://agi.university/on-the-likelihood-that-one-unknown-probability-exceeds-another-in-view-of-the-evidence-of-two-sample.md)
- [An empirical evaluation of Thompson Sampling](https://agi.university/an-empirical-evaluation-of-thompson-sampling.md)
- [What game are we playing? end-to-end learning in normal and extensive form games](https://agi.university/what-game-are-we-playing-end-to-end-learning-in-normal-and-extensive-form-games.md)
- [Intriguing properties of neural networks](https://agi.university/intriguing-properties-of-neural-networks.md)
- [Untitled](https://agi.university/intriguing-properties-of-neural-networks/untitled.md)
- [Explaining and harnessing adversarial examples](https://agi.university/explaining-and-harnessing-adversarial-examples.md)
- [The Landscape of Deep Reinforcement Learning](https://agi.university/the-landscape-of-deep-reinforcement-learning.md)
- [用因果影响图建模通用人工智能安全框架](https://agi.university/yong-yin-guo-ying-xiang-tu-jian-mo-tong-yong-ren-gong-zhi-neng-an-quan-kuang-jia.md)
- [test](https://agi.university/papers/test.md)
- [Measuring and avoiding side effects using relative reachability](https://agi.university/papers/papers.md)