
Evaluating Probabilistic Inference in Deep Learning: Beyond Marginal Predictions
A fundamental challenge for any intelligent system is prediction: given ...
read it

Epistemic Neural Networks
We introduce the epistemic neural network (ENN) as an interface for unce...
read it

Reinforcement Learning, Bit by Bit
Reinforcement learning agents have demonstrated remarkable achievements ...
read it

Hypermodels for Exploration
We study the use of hypermodels to represent epistemic uncertainty and g...
read it

Stochastic matrix games with bandit feedback
We study a version of the classical zerosum matrix game with unknown pa...
read it

Making Sense of Reinforcement Learning and Probabilistic Inference
Reinforcement learning (RL) combines a control problem with statistical ...
read it

Behaviour Suite for Reinforcement Learning
This paper introduces the Behaviour Suite for Reinforcement Learning, or...
read it

Metalearning of Sequential Strategies
In this report we review memorybased metalearning as a tool for buildi...
read it

Randomized Prior Functions for Deep Reinforcement Learning
Dealing with uncertainty is essential for efficient reinforcement learni...
read it

Scalable Coordinated Exploration in Concurrent Reinforcement Learning
We consider a team of reinforcement learning agents that concurrently op...
read it

The Uncertainty Bellman Equation and Exploration
We consider the exploration/exploitation problem in reinforcement learni...
read it

Noisy Networks for Exploration
We introduce NoisyNet, a deep reinforcement learning agent with parametr...
read it

On Optimistic versus Randomized Exploration in Reinforcement Learning
We discuss the relative merits of optimistic and randomized approaches t...
read it

Deep Qlearning from Demonstrations
Deep reinforcement learning (RL) has achieved several high profile succe...
read it

Deep Exploration via Randomized Value Functions
We study the use of randomized value functions to guide deep exploration...
read it

Minimax Regret Bounds for Reinforcement Learning
We consider the problem of provably optimal exploration in reinforcement...
read it

GaussianDirichlet Posterior Dominance in Sequential Learning
We consider the problem of sequential learning from categorical observat...
read it

On Lower Bounds for Regret in Reinforcement Learning
This is a brief technical note to clarify the state of lower bounds on r...
read it

Posterior Sampling for Reinforcement Learning Without Episodes
This is a brief technical note to clarify some of the issues with applyi...
read it

Why is Posterior Sampling Better than Optimism for Reinforcement Learning?
Computational results demonstrate that posterior sampling for reinforcem...
read it

Deep Exploration via Bootstrapped DQN
Efficient exploration in complex environments remains a major challenge ...
read it

Bootstrapped Thompson Sampling and Deep Exploration
This technical note presents a new approach to carrying out the kind of ...
read it

Nearoptimal Reinforcement Learning in Factored MDPs
Any reinforcement learning algorithm that applies to all Markov decision...
read it

Generalization and Exploration via Randomized Value Functions
We propose randomized leastsquares value iteration (RLSVI)  a new rei...
read it

(More) Efficient Reinforcement Learning via Posterior Sampling
Most provablyefficient learning algorithms introduce optimism about poo...
read it
Ian Osband
is this you? claim profile
Research Scientist at Google DeepMind since 2015, Data Scientist  Ads Metrics at Google Inc. 2014, Data Science Consultant at Credit Sesame 2014, Analyst  EM Credit Strategy at JPMorgan Chase from 20112012, Summer intern – Credit Derivatives Quant Research, Credit Trading at JPMorgan Chase 2010, Summer Intern at MVision Private Equity Advisers 2009, Doctor of Philosophy (PhD) in Management Science and Engineering at Stanford University from 20122016.