
Fully General Online Imitation Learning
In imitation learning, imitators and demonstrators are policies for pick...
read it

Learning Curve Theory
Recently a number of empirical "universal" scaling law papers have been ...
read it

Exact Reduction of Huge Action Spaces in General Reinforcement Learning
The reinforcement learning (RL) framework formalizes the notion of learn...
read it

Counterfactual Credit Assignment in ModelFree Reinforcement Learning
Credit assignment in reinforcement learning is the problem of measuring ...
read it

A Combinatorial Perspective on Transfer Learning
Human intelligence is characterized not only by the capacity to learn co...
read it

On Representing (Anti)Symmetric Functions
Permutationinvariant, equivariant, and covariant functions and antis...
read it

Logarithmic Pruning is All You Need
The Lottery Ticket Hypothesis is a conjecture that every large neural ne...
read it

Pessimism About Unknown Unknowns Inspires Conservatism
If we could define the set of all bad outcomes, we could hardcode an ag...
read it

Curiosity Killed the Cat and the Asymptotically Optimal Agent
Reinforcement learners are agents that learn to pick actions that lead t...
read it

Online Learning in Contextual Bandits using Gated Linear Networks
We introduce a new and completely online contextual bandit algorithm cal...
read it

Gated Linear Networks
This paper presents a family of backpropagationfree neural architecture...
read it

Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective
Can an arbitrarily intelligent reinforcement learning agent be kept unde...
read it

Fairness without Regret
A popular approach of achieving fairness in optimization problems is by ...
read it

Asymptotically Unambitious Artificial General Intelligence
General intelligence, the ability to solve arbitrary solvable problems, ...
read it

Conditions on Features for Temporal DifferenceLike Methods to Converge
The convergence of many reinforcement learning (RL) algorithms with line...
read it

Strong Asymptotic Optimality in General Environments
Reinforcement Learning agents are expected to eventually perform well. T...
read it

Performance Guarantees for Homomorphisms Beyond Markov Decision Processes
Most realworld problems have huge state and/or action spaces. Therefore...
read it

AGI Safety Literature Review
The development of Artificial General Intelligence (AGI) promises to be ...
read it

A GameTheoretic Analysis of the OffSwitch Game
The offswitch game is a game theoretic model of a highly intelligent ro...
read it

CountBased Exploration in Feature Space for Reinforcement Learning
We introduce a new countbased optimistic exploration algorithm for Rein...
read it

Universal Reinforcement Learning Algorithms: Survey and Experiments
Many stateoftheart reinforcement learning (RL) algorithms typically a...
read it

Reinforcement Learning with a Corrupted Reward Channel
No realworld reward function is perfect. Sensory errors and software bu...
read it

Loss Bounds and Time Complexity for Speed Priors
This paper establishes for the first time the predictive performance of ...
read it

Thompson Sampling is Asymptotically Optimal in General Environments
We discuss a variant of Thompson sampling for nonparametric reinforcemen...
read it

On the Computability of AIXI
How could we solve the machine learning and the artificial intelligence ...
read it

Bad Universal Priors and Notions of Optimality
A big open question of algorithmic information theory is the choice of t...
read it

A Topological Approach to Metaheuristics: Analytical Results on the BFS vs. DFS Algorithm Selection Problem
Search is a central problem in artificial intelligence, and BFS and DFS ...
read it

Compress and Control
This paper describes a new informationtheoretic policy evaluation techn...
read it

Robust Feature Selection by Mutual Information Distributions
Mutual information is widely used in artificial intelligence, in a descr...
read it

Extreme State Aggregation Beyond MDPs
We consider a Reinforcement Learning setup where an agent interacts with...
read it

A Novel IlluminationInvariant Loss for Monocular 3D Pose Estimation
The problem of identifying the 3D pose of a known object from a given 2D...
read it

Concentration and Confidence for Discrete Bayesian Sequence Predictors
Bayesian sequence prediction is a simple technique for predicting future...
read it

Optimistic Agents are Asymptotically Optimal
We use optimism to introduce generic asymptotically optimal reinforcemen...
read it

Probabilities on Sentences in an Expressive Logic
Automated reasoning about uncertain knowledge has many applications. One...
read it

Can Intelligence Explode?
The technological singularity refers to a hypothetical scenario in which...
read it

One Decade of Universal Artificial Intelligence
The first decade of this century has seen the nascency of the first math...
read it

3D Model Assisted Image Segmentation
The problem of segmenting a given image into coherent regions is importa...
read it

Principles of Solomonoff Induction and AIXI
We identify principles characterizing Solomonoff Induction by demands on...
read it

Feature Reinforcement Learning In Practice
Following a recent surge in using historybased methods for resolving pe...
read it

Asymptotically Optimal Agents
Artificial general intelligence aims to create agents capable of learnin...
read it

Time Consistent Discounting
A possibly immortal agent tries to maximise its summed discounted reward...
read it

Algorithmic Randomness as Foundation of Inductive Reasoning and Artificial Intelligence
This article is a brief personal account of the past, present, and futur...
read it

Model Selection by Loss Rank for Classification and Unsupervised Learning
Hutter (2007) recently introduced the loss rank principle (LoRP) as a ge...
read it

Featureless 2D3D Pose Estimation by Minimising an IlluminationInvariant Loss
The problem of identifying the 3D pose of a known object from a given 2D...
read it

Matching 2D Ellipses to 3D Circles with Application to Vehicle Pose Estimation
Finding the threedimensional representation of all or a part of a scene...
read it

Discrete MDL Predicts in Total Variation
The Minimum Description Length (MDL) principle selects the model that ha...
read it

A Monte Carlo AIXI Approximation
This paper introduces a principled approach for the design of a scalable...
read it

Open Problems in Universal Induction & Intelligence
Specialized intelligent systems can be found everywhere: finger print, h...
read it

Feature Reinforcement Learning: Part I: Unstructured MDPs
Generalpurpose, intelligent, learning agents cycle through sequences of...
read it

Predictive Hypothesis Identification
While statistics focusses on hypothesis testing and on estimating (prope...
read it