Drew Bagnell
14 papers · 2010–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (11) π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (5)
π
Interdisciplinary Bridge
π
Conference Polyglot
(5)
π
Academic Marathon
(14)
ποΈ
Keyword Collector
(68)
π
Century Club
(14)
π₯
Unstoppable
(5)
π
Trend Setter
π
Conference Pioneer
Conferences
ICML (7)
AISTATS (4)
ICLR (1)
NIPS (1)
RSS (1)
Top co-authors
Keywords
imitation learning
(5)
sequence modeling
(1)
policy optimization
(1)
online learning
(1)
high-dimensional modeling
(1)
document summarization
(1)
sample efficiency
(1)
maximum entropy
(1)
ensemble learning
(1)
convex optimization
(1)
structured prediction
(1)
sequential decision making
(1)
causal inference
(1)
supervised learning
(1)
trajectory prediction
(1)
human motion capture
(1)
policy learning
(1)
continuous optimization
(1)
inverse reinforcement learning
(1)
submodular optimization
(1)
Papers
Hybrid Reinforcement Learning from Offline Observation Alone
ICML 2024
Hybrid Inverse Reinforcement Learning
ICML 2024
Inverse Reinforcement Learning without Reinforcement Learning
ICML 2023
The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms
ICML 2023
Hybrid RL: Using both offline and online data can make RL efficient
ICLR 2023
Causal Imitation Learning under Temporally Correlated Noise
ICML 2022
Provably Efficient Imitation Learning from Observation Alone
ICML 2019
Near Optimal Bayesian Active Learning for Decision Making
AISTATS 2014
Perceiving, Learning, and Exploiting Object Affordances for Autonomous Pile Manipulation
RSS 2013
Learning Policies for Contextual Submodular Prediction
ICML 2013
SpeedBoost: Anytime Prediction with Uniform Near-Optimality
AISTATS 2012
Efficient high dimensional maximum entropy modeling via symmetric partition functions
NIPS 2012
A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
AISTATS 2011
Efficient Reductions for Imitation Learning
AISTATS 2010