Sebastian Flennerhag
9 papers · 2018–2023 · 4 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 ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (20) π£ Hot Topic Early Bird π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Silver
π
Triple Crown
π
Grand Slam
Venues
Top co-authors
Research topics
Machine Learning
(9)
Artificial Intelligence
(5)
Reinforcement Learning
(4)
Learning Paradigms Β· Artificial Intelligence
(4)
Methods
(4)
Optimization & Theory
(4)
Learning Paradigms Β· Machine Learning
(3)
Learning Types Β· Machine Learning
(3)
Deep Learning
(2)
Core AI
(2)
Learning Types Β· Deep Learning
(2)
Mathematics & Optimization
(1)
Applications
(1)
Architectures
(1)
Optimization
(1)
Keywords
reinforcement learning
(3)
neural network optimization
(2)
gradient descent
(2)
neural network
(2)
black-box optimization
(1)
manifold learning
(1)
transfer learning
(1)
computer vision
(1)
continuous control
(1)
constrained markov decision process
(1)
efficient exploration
(1)
last-iterate convergence
(1)
optimistic method
(1)
meta-reinforcement learning
(1)
intrinsic reward
(1)
activation function
(1)
diversity optimization
(1)
gradient descent ascent
(1)
constrained mdp
(1)
evolution strategy
(1)
Papers
Discovering Evolution Strategies via Meta-Black-Box Optimization
ICLR 2023
Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality
ICLR 2023
Optimistic Meta-Gradients
NeurIPS 2023
ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs
ICML 2023
Bootstrapped Meta-Learning
ICLR 2022
Introducing Symmetries to Black Box Meta Reinforcement Learning
AAAI 2022
Meta-Learning with Warped Gradient Descent
ICLR 2020
Transferring Knowledge across Learning Processes
ICLR 2019
Breaking the Activation Function Bottleneck through Adaptive Parameterization
NeurIPS 2018