AGI University
  • The AGI Landscape
  • 我们的愿景 Our vision
  • Papers
  • Rationality and intelligence
  • AI safety gridworlds
  • Modeling Friends and Foes
  • Forget-me-not-Process
  • Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study
  • Universal Transformers
  • Graph Convolutional Policy Network
  • Thermodynamics as a theory of decision-making with informationprocessing costs
  • Concrete Problems in AI Safety
  • A course in game theory
  • Theory of games and economic behavior
  • Reinforcement learning: An introduction 1e
  • Regret analysis of stochastic and nonstochastic multi-armed bandit problems
  • The nonstochastic multiarmed bandit problem
  • Information theory of decisions and actions
  • Clustering with bregman divergences
  • Quantal Response Equilibria for Normal Form Games
  • The numerics of gans
  • The Mechanics of n-Player Differentiable Games
  • Reactive bandits with attitude
  • Data clustering by markovian relaxation and the information bottleneck method
  • Information bottleneck for Gaussian variables
  • Bounded Rationality, Abstraction, and Hierarchical Decision-Making: An Information-Theoretic Optimal
  • Risk sensitive path integral control
  • Information, utility and bounded rationality
  • Hysteresis effects of changing the parameters of noncooperative games
  • The best of both worlds: stochastic and adversarial bandits
  • One practical algorithm for both stochastic and adversarial bandits
  • An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits
  • Friend-or-Foe Q-Learning in General-Sum Games
  • New criteria and a new algorithm for learning in multi-agent systems
  • Correlated Q-Learning
  • Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning
  • Learning against sequential opponents in repeated stochastic games
  • On the likelihood that one unknown probability exceeds another in view of the evidence of two sample
  • An empirical evaluation of Thompson Sampling
  • What game are we playing? end-to-end learning in normal and extensive form games
  • Intriguing properties of neural networks
    • Untitled
  • Explaining and harnessing adversarial examples
  • go-explore
  • The Landscape of Deep Reinforcement Learning
  • 用因果影响图建模通用人工智能安全框架
  • Papers
    • test
    • Measuring and avoiding side effects using relative reachability
Powered by GitBook
On this page
  • Concepts
  • Frameworks
  • Important Papers
  • Books
  • Probability
  • Reference

The AGI Landscape

Next我们的愿景 Our vision

Last updated 5 years ago

The AGI Landscape Ω\OmegaΩ is going to push the boundary of artificial general intelligence.

Ω=arg⁡max⁡θ AGI(θ)\mathbf{\Omega} = \underset{\theta}{\arg\max}\ \mathcal{AGI}(\theta)Ω=θargmax​ AGI(θ)

Concepts

Frameworks

  • : summary of general safety research in agi

  • : consider the problem of obtaining an out-of-sample extension for the adjacency spectral embedding, a procedure for embedding the vertices of a graph into Euclidean space.

  • : introduces a general definition of side effects, based on relative reachability of states compared to a default state, that avoids these undesirable incentives.

Nov

Books

Probability

  • P. Billingsley Probability and Measure (3rd Edition). Chapters 1-30 contain a more careful and detailed treatment of some of the topics of this semester, in particular the measure-theory background. Recommended for students who have not done measure theory.

There are many other books at roughly the same ``first year graduate" level. Here are my personal comments on some.

Reference

R. Durrett .

R. Leadbetter et al is a new book giving a careful treatment of the measure-theory background.

D. Khoshnevisan is a well-written concise account of the key topics in 205AB.

R. Bhattacharya and E. C. Waymire is another well-written account, mostly on the 205A topics.

K.L. Chung covers many of the topics of 205A: more leisurely than Durrett and more focused than Billingsley.

D. Williams has a uniquely enthusiastic style; concise treatment emphasizes usefulness of martingales.

Y.S. Chow and H. Teicher. Uninspired exposition, but has useful variations on technical topics such as inequalities for sums and for martingales.

R.M. Dudley. Best account of the functional analysis and metric space background relevant for research in theoretical probability.

B. Fristedt and L. Gray. 700 pages allow coverage of broad range of topics in probability and stochastic processes.

L. Breiman. Classical; concise and broad coverage.

O. Kallenberg . Quoting an amazon.com reviewer: ``.... a compendium of all the relevant results of probability ..... similar in breadth and depth to Loeve's classical text of the mid 70's. It is not suited as a textbook, as it lacks the many examples that are needed to absorb the theory at a first pass. It works best as a reference book or a "second pass" textbook."

John B. Walsh . New in 2012. Looks very nice -- concise treatment with quite challenging exercises developing part of theory.

George Roussas . Recent treatment of classical content.

Santosh Venkatesh . Unique new book, intertwining a broad range of undergraduate and graduate-level topics for an applied audience.

I. Florescu . Very clearly written, and with 550 pages gives a broad coverage of topics including intro to SDEs.

Jim Pitman has his linked to the Durrett text; these notes cover more ground than my course will! Also some for the Stanford courses equivalent to our 205AB.

The Books: , by Professor David Aldous from UC Berkeley.

The Importance of Sampling in Meta-Reinforcement Learning
Inequity aversion improves cooperation in intertemporal social dilemmas
Probability: Theory and Examples (4th edition)
A Basic Course in Measure and Probability: Theory for Applications
Probability
A Basic Course in Probability Theory
A Course in Probability Theory
Probability with Martingales
Probability Theory: Independence, Interchangeability, Martingales
Real Analysis and Probability
A Modern Approach to Probability Theory
Probability
Foundations of Modern Probability
Knowing the Odds: An Introduction to Probability
An Introduction to Measure-Theoretic Probability
The Theory of Probability: Explorations and Applications
Probability and Stochastic Processes
very useful lecture notes
lecture notes by Amir Dembo
https://www.stat.berkeley.edu/~aldous/205B/index.html
Kolmogorov complexity
https://github.com/deepmind/pysc2
https://pythonprogramming.net/starcraft-ii-ai-python-sc2-tutorial/
Important Papers
Universal Transformers
The Forget-me-not Process
AGI Safety Literature Review
Out-of-sample extension of graph adjacency spectral embedding
Alignment for Advanced Machine Learning Systems
Measuring and avoiding side effects using relative reachability