Brendan O’Donoghue
5 papers · 2018–2023 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (2) 🏃 Academic Marathon (5)
🐝
Cross-Pollinator
(9)
🗺️
Taxonomy Completionist
(14)
📈
Trend Setter
Conferences
ICML (4)
UAI (1)
Top co-authors
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
ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs
ICML 2023
Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization
ICML 2023
Matrix games with bandit feedback
UAI 2021
The Uncertainty Bellman Equation and Exploration
ICML 2018
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
ICML 2018