Brendan O'Donoghue

Publication Activity (10 Years)

Years Active: 2011-2023
Publications (10 Years): 45

Top Topics

Markov Decision Process

Bucket Elimination

Reinforcement Learning

Top Venues

Publications

Brendan O'Donoghue
Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization. ICML (2023)
Jean Tarbouriech, Tor Lattimore, Brendan O'Donoghue
Probabilistic Inference in Reinforcement Learning Done Right. NeurIPS (2023)
Brendan O'Donoghue
Efficient exploration via epistemic-risk-seeking policy optimization. CoRR (2023)
Sebastian Flennerhag, Tom Zahavy, Brendan O'Donoghue, Hado Philip van Hasselt, András György, Satinder Singh
Optimistic Meta-Gradients. NeurIPS (2023)
Ted Moskovitz, Brendan O'Donoghue, Vivek Veeriah, Sebastian Flennerhag, Satinder Singh, Tom Zahavy
ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs. ICML (2023)
Jean Tarbouriech, Tor Lattimore, Brendan O'Donoghue
Probabilistic Inference in Reinforcement Learning Done Right. CoRR (2023)
Khimya Khetarpal, Claire Vernade, Brendan O'Donoghue, Satinder Singh, Tom Zahavy
POMRL: No-Regret Learning-to-Plan with Increasing Horizons. Trans. Mach. Learn. Res. 2023 (2023)
Sebastian Flennerhag, Tom Zahavy, Brendan O'Donoghue, Hado van Hasselt, András György, Satinder Singh
Optimistic Meta-Gradients. CoRR (2023)
Ted Moskovitz, Brendan O'Donoghue, Vivek Veeriah, Sebastian Flennerhag, Satinder Singh, Tom Zahavy
ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs. CoRR (2023)
Khimya Khetarpal, Claire Vernade, Brendan O'Donoghue, Satinder Singh, Tom Zahavy
POMRL: No-Regret Learning-to-Plan with Increasing Horizons. CoRR (2022)
Brendan O'Donoghue
On the connection between Bregman divergence and value in regularized Markov decision processes. CoRR (2022)
Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Xiuyuan Lu, Morteza Ibrahimi, Dieterich Lawson, Botao Hao, Brendan O'Donoghue, Benjamin Van Roy
The Neural Testbed: Evaluating Joint Predictions. NeurIPS (2022)
Brendan O'Donoghue
Variational Bayesian Reinforcement Learning with Regret Bounds. NeurIPS (2021)
Tom Zahavy, Brendan O'Donoghue, André Barreto, Volodymyr Mnih, Sebastian Flennerhag, Satinder Singh
Discovering Diverse Nearly Optimal Policies withSuccessor Features. CoRR (2021)
Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Botao Hao, Morteza Ibrahimi, Dieterich Lawson, Xiuyuan Lu, Brendan O'Donoghue, Benjamin Van Roy
Evaluating Predictive Distributions: Does Bayesian Deep Learning Work? CoRR (2021)
Brendan O'Donoghue, Tor Lattimore
Variational Bayesian Optimistic Sampling. NeurIPS (2021)
David L. Applegate, Mateo Díaz, Oliver Hinder, Haihao Lu, Miles Lubin, Brendan O'Donoghue, Warren Schudy
Practical Large-Scale Linear Programming using Primal-Dual Hybrid Gradient. NeurIPS (2021)
Brendan O'Donoghue
Operator Splitting for a Homogeneous Embedding of the Linear Complementarity Problem. SIAM J. Optim. 31 (3) (2021)
Brendan O'Donoghue, Tor Lattimore, Ian Osband
Matrix games with bandit feedback. UAI (2021)
Junzi Zhang, Jongho Kim, Brendan O'Donoghue, Stephen P. Boyd
Sample Efficient Reinforcement Learning with REINFORCE. AAAI (2021)
Tom Zahavy, Brendan O'Donoghue, Guillaume Desjardins, Satinder Singh
Reward is enough for convex MDPs. NeurIPS (2021)
Tom Zahavy, André Barreto, Daniel J. Mankowitz, Shaobo Hou, Brendan O'Donoghue, Iurii Kemaev, Satinder Baveja Singh
Discovering a set of policies for the worst case reward. CoRR (2021)
Brendan O'Donoghue, Tor Lattimore
Variational Bayesian Optimistic Sampling. CoRR (2021)
Tom Zahavy, Brendan O'Donoghue, Guillaume Desjardins, Satinder Singh
Reward is enough for convex MDPs. CoRR (2021)
Tom Zahavy, André Barreto, Daniel J. Mankowitz, Shaobo Hou, Brendan O'Donoghue, Iurii Kemaev, Satinder Singh
Discovering a set of policies for the worst case reward. ICLR (2021)
Brendan O'Donoghue, Tor Lattimore, Ian Osband
Stochastic matrix games with bandit feedback. CoRR (2020)
Brendan O'Donoghue, Ian Osband, Catalin Ionescu
Making Sense of Reinforcement Learning and Probabilistic Inference. ICLR (2020)
Junzi Zhang, Jongho Kim, Brendan O'Donoghue, Stephen P. Boyd
Sample Efficient Reinforcement Learning with REINFORCE. CoRR (2020)
Junzi Zhang, Brendan O'Donoghue, Stephen P. Boyd
Globally Convergent Type-I Anderson Acceleration for Nonsmooth Fixed-Point Iterations. SIAM J. Optim. 30 (4) (2020)
Brendan O'Donoghue, Ian Osband, Catalin Ionescu
Making Sense of Reinforcement Learning and Probabilistic Inference. CoRR (2020)
Vinod Nair, Sergey Bartunov, Felix Gimeno, Ingrid von Glehn, Pawel Lichocki, Ivan Lobov, Brendan O'Donoghue, Nicolas Sonnerat, Christian Tjandraatmadja, Pengming Wang, Ravichandra Addanki, Tharindi Hapuarachchi, Thomas Keck, James Keeling, Pushmeet Kohli, Ira Ktena, Yujia Li, Oriol Vinyals, Yori Zwols
Solving Mixed Integer Programs Using Neural Networks. CoRR (2020)
Chongli Qin, Krishnamurthy (Dj) Dvijotham, Brendan O'Donoghue, Rudy Bunel, Robert Stanforth, Sven Gowal, Jonathan Uesato, Grzegorz Swirszcz, Pushmeet Kohli
Verification of Non-Linear Specifications for Neural Networks. CoRR (2019)
Brendan O'Donoghue, Chris J. Maddison
Hamiltonian descent for composite objectives. NeurIPS (2019)
Chongli Qin, Krishnamurthy (Dj) Dvijotham, Brendan O'Donoghue, Rudy Bunel, Robert Stanforth, Sven Gowal, Jonathan Uesato, Grzegorz Swirszcz, Pushmeet Kohli
Verification of Non-Linear Specifications for Neural Networks. ICLR (Poster) (2019)
Brendan O'Donoghue
Variational Bayesian Reinforcement Learning with Regret Bounds. CoRR (2018)
Brendan O'Donoghue, Ian Osband, Rémi Munos, Volodymyr Mnih
The Uncertainty Bellman Equation and Exploration. ICML (2018)
Jonathan Uesato, Brendan O'Donoghue, Aäron van den Oord, Pushmeet Kohli
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks. CoRR (2018)
Chris J. Maddison, Daniel Paulin, Yee Whye Teh, Brendan O'Donoghue, Arnaud Doucet
Hamiltonian Descent Methods. CoRR (2018)
Edward Grefenstette, Robert Stanforth, Brendan O'Donoghue, Jonathan Uesato, Grzegorz Swirszcz, Pushmeet Kohli
Strength in Numbers: Trading-off Robustness and Computation via Adversarially-Trained Ensembles. CoRR (2018)
Jonathan Uesato, Brendan O'Donoghue, Pushmeet Kohli, Aäron van den Oord
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks. ICML (2018)
Krishnamurthy Dvijotham, Sven Gowal, Robert Stanforth, Relja Arandjelovic, Brendan O'Donoghue, Jonathan Uesato, Pushmeet Kohli
Training verified learners with learned verifiers. CoRR (2018)
Brendan O'Donoghue, Rémi Munos, Koray Kavukcuoglu, Volodymyr Mnih
Combining policy gradient and Q-learning. ICLR (Poster) (2017)
Brendan O'Donoghue, Ian Osband, Rémi Munos, Volodymyr Mnih
The Uncertainty Bellman Equation and Exploration. CoRR (2017)
Brendan O'Donoghue, Eric Chu, Neal Parikh, Stephen P. Boyd
Conic Optimization via Operator Splitting and Homogeneous Self-Dual Embedding. J. Optim. Theory Appl. 169 (3) (2016)
Brendan O'Donoghue, Rémi Munos, Koray Kavukcuoglu, Volodymyr Mnih
PGQ: Combining policy gradient and Q-learning. CoRR (2016)
Yuanming Shi, Jun Zhang, Brendan O'Donoghue, Khaled Ben Letaief
Large-Scale Convex Optimization for Dense Wireless Cooperative Networks. IEEE Trans. Signal Process. 63 (18) (2015)
Yuanming Shi, Jun Zhang, Brendan O'Donoghue, Khaled Ben Letaief
Large-Scale Convex Optimization for Dense Wireless Cooperative Networks. CoRR (2015)
Brendan O'Donoghue, Emmanuel J. Candès
Adaptive Restart for Accelerated Gradient Schemes. Found. Comput. Math. 15 (3) (2015)
Stephen P. Boyd, Mark T. Müller, Brendan O'Donoghue, Yang Wang
Performance Bounds and Suboptimal Policies for Multi-Period Investment. Found. Trends Optim. 1 (1) (2014)
Tom Goldstein, Brendan O'Donoghue, Simon Setzer, Richard G. Baraniuk
Fast Alternating Direction Optimization Methods. SIAM J. Imaging Sci. 7 (3) (2014)
Brendan O'Donoghue, Yang Wang, Stephen P. Boyd
Iterated approximate value functions. ECC (2013)
Brendan O'Donoghue, Giorgos Stathopoulos, Stephen P. Boyd
A Splitting Method for Optimal Control. IEEE Trans. Control. Syst. Technol. 21 (6) (2013)
Brendan O'Donoghue, Yang Wang, Stephen P. Boyd
Min-max approximate dynamic programming. CACSD (2011)