Ian Osband

发表

Deep Exploration via Bootstrapped DQN

Benjamin Van Roy, Charles Blundell, Ian Osband, 2016, NIPS.

Meta-learning of Sequential Strategies pdf

Yee Whye Teh, Razvan Pascanu, Nando de Freitas, 2019, ArXiv.

Noisy Networks for Exploration pdf

Shane Legg, Alex Graves, Demis Hassabis, 2017, ICLR.

Generalization and Exploration via Randomized Value Functions pdf

Benjamin Van Roy, Ian Osband, Zheng Wen, 2014, ICML.

Learning from Demonstrations for Real World Reinforcement Learning pdf

Tom Schaul, Andrew Sendonaris, Joel Z. Leibo, 2017, ArXiv.

(More) Efficient Reinforcement Learning via Posterior Sampling

Benjamin Van Roy, Ian Osband, Daniel Russo, 2013, NIPS.

Randomized Prior Functions for Deep Reinforcement Learning

Albin Cassirer, Ian Osband, John Aslanides, 2018, NeurIPS.

Behaviour Suite for Reinforcement Learning pdf

Tor Lattimore, Richard S. Sutton, Csaba Szepesvári, 2019, ICLR.

Near-optimal Reinforcement Learning in Factored MDPs

Benjamin Van Roy, Ian Osband, Ian Osband, 2014, NIPS.

Bootstrapped Thompson Sampling and Deep Exploration pdf

Benjamin Van Roy, Ian Osband, Ian Osband, 2015, ArXiv.

Deep Learning for Time Series Modeling CS 229 Final Project Report

Ian Osband, Enzo Busseti, Scott Wong, 2012 .

Minimax Regret Bounds for Reinforcement Learning

Rémi Munos, Ian Osband, Mohammad Gheshlaghi Azar, 2017, ICML.

Gaussian-Dirichlet Posterior Dominance in Sequential Learning pdf

Benjamin Van Roy, Ian Osband, Ian Osband, 2017, ArXiv.

Deep Exploration via Randomized Value Functions

Zheng Wen, Benjamin Van Roy, Ian Osband, 2017, J. Mach. Learn. Res..

A Tutorial on Thompson Sampling

Benjamin Van Roy, Ian Osband, Daniel Russo, 2017, Found. Trends Mach. Learn..

Risk versus Uncertainty in Deep Learning: Bayes, Bootstrap and the Dangers of Dropout

Ian Osband, Ian Osband, 2016 .

From Predictions to Decisions: The Importance of Joint Predictive Distributions

Benjamin Van Roy, Zheng Wen, Ian Osband, 2021, 2107.09224.

The Neural Testbed: Evaluating Joint Predictions

Benjamin Van Roy, Zheng Wen, Ian Osband, 2021, NeurIPS.

Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping

Benjamin Van Roy, Zheng Wen, Ian Osband, 2022, Trans. Mach. Learn. Res..

Robustness of Epinets against Distributional Shifts

Benjamin Van Roy, Ian Osband, Sven Gowal, 2022, ArXiv.

Fine-Tuning Language Models via Epistemic Neural Networks

Geoffrey Irving, Ian Osband, B. V. Roy, 2022, ArXiv.

Near-optimal Regret Bounds for Reinforcement Learning in Factored MDPs pdf

Benjamin Van Roy, Ian Osband, Ian Osband, 2014, ArXiv.

Deep Q-learning From Demonstrations

Tom Schaul, Andrew Sendonaris, Joel Z. Leibo, 2017, AAAI.

Why is Posterior Sampling Better than Optimism for Reinforcement Learning? pdf

Benjamin Van Roy, Ian Osband, Ian Osband, 2016, ICML.

Scalable Coordinated Exploration in Concurrent Reinforcement Learning

Benjamin Van Roy, Ian Osband, Maria Dimakopoulou, 2018, NeurIPS.

The Uncertainty Bellman Equation and Exploration

Ian Osband, Brendan O'Donoghue, Volodymyr Mnih, 2017, ICML.

Model-based Reinforcement Learning and the Eluder Dimension

Benjamin Van Roy, Ian Osband, Ian Osband, 2014, NIPS.

Stochastic matrix games with bandit feedback pdf

Tor Lattimore, Ian Osband, Brendan O'Donoghue, 2020, ArXiv.

Making Sense of Reinforcement Learning and Probabilistic Inference

Ian Osband, Catalin Ionescu, Brendan O'Donoghue, 2020, ICLR.

Matrix games with bandit feedback

Tor Lattimore, Ian Osband, Brendan O'Donoghue, 2020, UAI.

On Lower Bounds for Regret in Reinforcement Learning pdf

Benjamin Van Roy, Ian Osband, Ian Osband, 2016, ArXiv.

Epistemic Neural Networks

Benjamin Van Roy, Zheng Wen, Ian Osband, 2021, ArXiv.

Fine-Tuning Language Models via Epistemic Neural Networks

Benjamin Van Roy, Ian Osband, J. Aslanides, 2022, ArXiv.

Evaluating High-Order Predictive Distributions in Deep Learning

Benjamin Van Roy, Zheng Wen, Ian Osband, 2022, UAI.

Reinforcement Learning, Bit by Bit pdf

Zheng Wen, Benjamin Van Roy, Ian Osband, 2021, Found. Trends Mach. Learn..

Hypermodels for Exploration pdf

Benjamin Van Roy, Ian Osband, Xiuyuan Lu, 2020, ICLR.

The Neural Testbed: Evaluating Predictive Distributions

Benjamin Van Roy, Ian Osband, Dieterich Lawson, 2022 .

Evaluating Predictive Distributions: Does Bayesian Deep Learning Work? pdf

Seyed Mohammad Asghari, Benjamin Van Roy, Ian Osband, 2021, ArXiv.

Approximate Thompson Sampling via Epistemic Neural Networks

Benjamin Van Roy, Ian Osband, Xiuyuan Lu, 2023, UAI.

Noisy Networks for Exploration

D. Hassabis, R. Munos, S. Legg, 2017, ICLR.