research
∙
07/05/2022
Neural Networks and the Chomsky Hierarchy
Reliable generalization lies at the heart of safe ML and AI. However, un...
share
research
∙
11/04/2021
Model-Free Risk-Sensitive Reinforcement Learning
We extend temporal-difference (TD) learning in order to obtain risk-sens...
research
∙
10/20/2021
Shaking the foundations: delusions in sequence models for interaction and control
The recent phenomenal success of language models has reinvigorated machi...
research
∙
03/05/2021
Causal Analysis of Agent Behavior for AI Safety
As machine learning systems become more powerful they also become increa...
research
∙
02/02/2021
Agent Incentives: A Causal Perspective
We present a framework for analysing agent incentives using causal influ...
research
∙
10/23/2020
Algorithms for Causal Reasoning in Probability Trees
Probability trees are one of the simplest models of causal generative pr...
research
∙
10/21/2020
Meta-trained agents implement Bayes-optimal agents
Memory-based meta-learning is a powerful technique to build agents that ...
research
∙
09/03/2020
Action and Perception as Divergence Minimization
We introduce a unified objective for action and perception of intelligen...
research
∙
05/15/2019
Meta reinforcement learning as task inference
Humans achieve efficient learning by relying on prior knowledge about th...
research
∙
05/08/2019
Meta-learning of Sequential Strategies
In this report we review memory-based meta-learning as a tool for buildi...
research
∙
02/26/2019
Understanding Agent Incentives using Causal Influence Diagrams, Part I: Single Action Settings
Agents are systems that optimize an objective function in an environment...
research
∙
10/19/2018
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
We propose a unified mechanism for achieving coordination and communicat...
research
∙
10/19/2018
Intrinsic Social Motivation via Causal Influence in Multi-Agent RL
We derive a new intrinsic social motivation for multi-agent reinforcemen...
research
∙
06/30/2018
Modeling Friends and Foes
How can one detect friendly and adversarial behavior from raw data? Dete...
research
∙
11/27/2017
AI Safety Gridworlds
We present a suite of reinforcement learning environments illustrating v...
research
∙
10/06/2016
Human Decision-Making under Limited Time
Subjective expected utility theory assumes that decision-makers possess ...
research
∙
04/18/2016
Memory shapes time perception and intertemporal choices
There is a consensus that human and non-human subjects experience tempor...
research
∙
12/21/2015
Information-Theoretic Bounded Rationality
Bounded rationality, that is, decision-making and planning under resourc...
research
∙
05/26/2015
Belief Flows of Robust Online Learning
This paper introduces a new probabilistic model for online learning whic...
research
∙
07/15/2014
Subjectivity, Bayesianism, and Causality
Bayesian probability theory is one of the most successful frameworks to ...
research
∙
04/22/2014
An Adversarial Interpretation of Information-Theoretic Bounded Rationality
Recently, there has been a growing interest in modeling planning with in...
research
∙
03/18/2013
Generalized Thompson Sampling for Sequential Decision-Making and Causal Inference
Recently, it has been shown how sampling actions from the predictive dis...
research
∙
06/09/2012
A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function
We propose a novel Bayesian approach to solve stochastic optimization pr...
research
∙
05/17/2012
Free Energy and the Generalized Optimality Equations for Sequential Decision Making
The free energy functional has recently been proposed as a variational p...
research
∙
11/03/2011
Bayesian Causal Induction
Discovering causal relationships is a hard task, often hindered by the n...
research
∙
07/28/2011
Information, Utility & Bounded Rationality
Perfectly rational decision-makers maximize expected utility, but crucia...
research
∙
02/16/2010
Convergence of Bayesian Control Rule
Recently, new approaches to adaptive control have sought to reformulate ...
research
∙
02/07/2010
A Minimum Relative Entropy Controller for Undiscounted Markov Decision Processes
Adaptive control problems are notoriously difficult to solve even in the...
research
∙
11/26/2009
A conversion between utility and information
Rewards typically express desirabilities or preferences over a set of al...
research
∙
11/26/2009