Articles by Pedro A. Ortega

Claim page

Pedro A. Ortega

Activity

Upvotes

Folders

Articles

Neural Networks and the Chomsky Hierarchy

6 October 2022 by Grégoire Delétang and others at

Stanford University

Machine Learning, Artificial Intelligence

Model-Free Risk-Sensitive Reinforcement Learning

4 November 2021 by Grégoire Delétang and others

Machine Learning

Shaking the foundations: delusions in sequence models for interaction and control

20 October 2021 by Pedro Ortega and others

Machine Learning, Artificial Intelligence

Agent Incentives: A Causal Perspective

15 March 2021 by Tom Everitt and others

Artificial Intelligence, Machine Learning

Causal Analysis of Agent Behavior for AI Safety

5 March 2021 by Grégoire Déletang and others

Artificial Intelligence, Machine Learning

Algorithms for Causal Reasoning in Probability Trees

12 November 2020 by Tim Genewein and others

Artificial Intelligence, Machine Learning

Meta-trained agents implement Bayes-optimal agents

21 October 2020 by Vladimir Mikulik and others

Artificial Intelligence, Machine Learning

Action and Perception as Divergence Minimization

5 October 2020 by Danijar Hafner and others

Artificial Intelligence, Information Theory

Meta reinforcement learning as task inference

22 October 2019 by Jan Humplik and others

Machine Learning, Artificial Intelligence

Meta-learning of Sequential Strategies

18 July 2019 by Pedro Ortega and others

Machine Learning, Artificial Intelligence

Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings

27 February 2019 by Tom Everitt and others

Artificial Intelligence, Machine Learning

Intrinsic Social Motivation via Causal Influence in Multi-Agent RL

14 December 2018 by Natasha Jaques and others

Machine Learning, Artificial Intelligence

Modeling Friends and Foes

30 June 2018 by Pedro Ortega and Shane Legg

Artificial Intelligence

AI Safety Gridworlds

28 November 2017 by Jan Leike and others

Machine Learning, Artificial Intelligence

Human Decision-Making under Limited Time

6 October 2016 by Pedro Ortega and Alan Stocker

Machine Learning, Artificial Intelligence

Memory shapes time perception and intertemporal choices

29 May 2016 by Pedro Ortega and Naftali Tishby

Neurons and Cognition, Artificial Intelligence

Information-Theoretic Bounded Rationality

21 December 2015 by Pedro Ortega and others

Machine Learning, Artificial Intelligence

Belief Flows of Robust Online Learning

26 May 2015 by Pedro Ortega and others

Machine Learning

Subjectivity, Bayesianism, and Causality

16 September 2014 by Pedro Ortega

Artificial Intelligence, Methodology

An Adversarial Interpretation of Information-Theoretic Bounded Rationality

22 April 2014 by Pedro Ortega and Daniel Lee

Artificial Intelligence

Generalized Thompson Sampling for Sequential Decision-Making and Causal Inference

18 March 2013 by Pedro Ortega and Daniel Braun

Artificial Intelligence, Machine Learning

Metabolic cost as an organizing principle for cooperative learning

9 February 2013 by David Balduzzi and others

Neurons and Cognition, Machine Learning

A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function

10 November 2012 by Pedro Ortega and others

Machine Learning, Artificial Intelligence

Thermodynamics as a theory of decision-making with information processing costs

30 July 2012 by Pedro Ortega and Daniel Braun

Statistics Theory, Optimization and Control

Free Energy and the Generalized Optimality Equations for Sequential Decision Making

17 May 2012 by Pedro Ortega and Daniel Braun

Machine Learning, Artificial Intelligence

Bayesian Causal Induction

30 November 2011 by Pedro Ortega

Machine Learning, Artificial Intelligence

Information, Utility & Bounded Rationality

28 July 2011 by Pedro Ortega and Daniel Braun

Artificial Intelligence

Logic, Reasoning under Uncertainty and Causality

16 August 2010 by Pedro Ortega

Statistics Theory

An axiomatic formalization of bounded rationality based on a utility-information equivalence

6 July 2010 by Pedro Ortega and Daniel Braun

Artificial Intelligence, Computer Science and Game Theory

Convergence of Bayesian Control Rule

16 February 2010 by Pedro Ortega and Daniel Braun

Artificial Intelligence, Machine Learning

This is an AI-generated summary

Key points

Topics

Machine Learning Artificial Intelligence Statistics Theory Information Theory Neurons and Cognition Systems and Control Optimization and Control Computer Science and Game Theory Computation and Language Formal Languages and Automata Theory Neural and Evolutionary Computing Multiagent Systems Methodology Adaptation and Self-Organizing Systems Robotics