Brendan O’Donoghue
5 papers · 2018–2023 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(14)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
regret bound
(2)
policy optimization
(2)
reinforcement learning
(1)
adversarial robustness
(1)
game theory
(1)
function approximation
(1)
epistemic uncertainty
(1)
posterior distribution
(1)
exploration-exploitation tradeoff
(1)
bandit feedback
(1)
ucb algorithm
(1)
constrained markov decision process
(1)
multi-armed bandit
(1)
zero-sum game
(1)
matrix game
(1)
last-iterate convergence
(1)
optimistic method
(1)
exploration strategy
(1)
adversarial example
(1)
gradient-free optimization
(1)
Papers
Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization
ICML 2023
ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs
ICML 2023
Matrix games with bandit feedback
UAI 2021
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
ICML 2018
The Uncertainty Bellman Equation and Exploration
ICML 2018