
Detecting Modularity in Deep Neural Networks
A neural network is modular to the extent that parts of its computationa...
read it

CrossDomain Imitation Learning via Optimal Transport
Crossdomain imitation learning studies how to leverage expert demonstra...
read it

Scalable Online Planning via Reinforcement Learning FineTuning
Lookahead search has been a critical component of recent AI successes, s...
read it

Explore and Control with Adversarial Surprise
Reinforcement learning (RL) provides a framework for learning goaldirec...
read it

The MineRL BASALT Competition on Learning from Human Feedback
The last decade has seen a significant increase of interest in deep lear...
read it

Learning the Preferences of Uncertain Humans with Inverse Decision Theory
Existing observational approaches for learning human preferences, such a...
read it

MADE: Exploration via Maximizing Deviation from Explored Regions
In online reinforcement learning (RL), efficient exploration remains par...
read it

Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism
Offline (or batch) reinforcement learning (RL) algorithms seek to learn ...
read it

Clusterability in Neural Networks
The learned weights of a neural network have often been considered devoi...
read it

Accumulating Risk Capital Through Investing in Cooperation
Recent work on promoting cooperation in multiagent learning has resulte...
read it

MultiPrincipal Assistance Games: Definition and Collegial Mechanisms
We introduce the concept of a multiprincipal assistance game (MPAG), an...
read it

Understanding Learned Reward Functions
In many realworld tasks, it is not possible to procedurally specify an ...
read it

Emergent Complexity and Zeroshot Transfer via Unsupervised Environment Design
A wide range of reinforcement learning (RL) problems  including robustn...
read it

DERAIL: Diagnostic Environments for Reward And Imitation Learning
The objective of many realworld tasks is complex and difficult to proce...
read it

The MAGICAL Benchmark for Robust Imitation
Imitation Learning (IL) algorithms are typically evaluated in the same e...
read it

SLIP: Learning to Predict in Unknown Dynamical Systems with LongTerm Memory
We present an efficient and practical (polynomial time) algorithm for on...
read it

MultiPrincipal Assistance Games
Assistance games (also known as cooperative inverse reinforcement learni...
read it

Quantifying Differences in Reward Functions
For many tasks, the reward function is too complex to be specified proce...
read it

Neural Networks are Surprisingly Modular
The learned weights of a neural network are often considered devoid of s...
read it

Bayesian Relational Memory for Semantic Visual Navigation
We introduce a new memory architecture, Bayesian Relational Memory (BRM)...
read it

Adversarial Policies: Attacking Deep Reinforcement Learning
Deep reinforcement learning (RL) policies are known to be vulnerable to ...
read it

Inverse reinforcement learning for video games
Deep reinforcement learning achieves superhuman performance in a range o...
read it

Learning and Planning with a Semantic Model
Building deep reinforcement learning agents that can generalize and adap...
read it

Learning Plannable Representations with Causal InfoGAN
In recent years, deep generative models have been shown to 'imagine' con...
read it

An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
Our goal is for AI systems to correctly identify and act according to th...
read it

DiscreteContinuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms
Despite the recent successes of probabilistic programming languages (PPL...
read it

On DiscreteContinuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms
Despite of the recent successes of probabilistic programming languages (...
read it

Inverse Reward Design
Autonomous agents optimize the reward function we give them. What they d...
read it

Servant of Many Masters: Shifting priorities in Paretooptimal sequential decisionmaking
It is often argued that an agent making decisions on behalf of two or mo...
read it

Should Robots be Obedient?
Intuitively, obedience  following the order that a human gives  seem...
read it

The OffSwitch Game
It is clear that one of the primary tools we can use to mitigate the pot...
read it

Swift: Compiled Inference for Probabilistic Programming Languages
A probabilistic program defines a probability measure over its semantic ...
read it

Cooperative Inverse Reinforcement Learning
For an autonomous system to be helpful to humans and to pose no unwarran...
read it

Towards Practical Bayesian Parameter and State Estimation
Joint state and parameter estimation is a core problem for dynamic Bayes...
read it

Research Priorities for Robust and Beneficial Artificial Intelligence
Success in the quest for artificial intelligence has the potential to br...
read it

Probabilistic ModelBased Approach for Heart Beat Detection
Nowadays, hospitals are ubiquitous and integral to modern society. Patie...
read it

Selecting Computations: Theory and Applications
Sequential decision problems are often approximately solvable by simulat...
read it

Automated Construction of Sparse Bayesian Networks from Unstructured Probabilistic Models and Domain Information
An algorithm for automated construction of a sparse Bayesian network giv...
read it

FineGrained DecisionTheoretic Search Control
Decisiontheoretic control of search has previously used as its basic un...
read it

Image Segmentation in Video Sequences: A Probabilistic Approach
"Background subtraction" is an old technique for finding moving objects ...
read it

Learning the Structure of Dynamic Probabilistic Networks
Dynamic probabilistic networks are a compact representation of complex s...
read it

RaoBlackwellised Particle Filtering for Dynamic Bayesian Networks
Particle filters (PFs) are powerful samplingbased inference/learning al...
read it

Variational MCMC
We propose a new class of learning algorithms that combines variational ...
read it

Decayed MCMC Filtering
Filteringestimating the state of a partially observable Markov proces...
read it

A Generalized Mean Field Algorithm for Variational Inference in Exponential Families
The mean field methods, which entail approximating intractable probabili...
read it

Graph partition strategies for generalized mean field inference
An autonomous variational inference algorithm for arbitrary graphical mo...
read it

A compact, hierarchical Qfunction decomposition
Previous work in hierarchical reinforcement learning has faced a dilemma...
read it

Improving Gradient Estimation by Incorporating Sensor Data
An efficient policy search algorithm should estimate the local gradient ...
read it

RAPID: A Reachable Anytime Planner for Impreciselysensed Domains
Despite the intractability of generic optimal partially observable Marko...
read it

Gibbs Sampling in OpenUniverse Stochastic Languages
Languages for openuniverse probabilistic models (OUPMs) can represent s...
read it