Siddhant Jayakumar
6 papers · 2018–2021 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π£ Hot Topic Early Bird πΊοΈ Taxonomy Completionist (16) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (3)
π
Cross-Pollinator
(12)
π
Trend Setter
Conferences
ICML (3)
NIPS (2)
AISTATS (1)
Top co-authors
Keywords
reinforcement learning
(3)
sparse training
(2)
multi-task learning
(2)
neural network pruning
(2)
model compression
(2)
policy gradient
(1)
curriculum learning
(1)
knowledge transfer
(1)
knowledge distillation
(1)
policy learning
(1)
computational efficiency
(1)
episodic memory
(1)
gradient descent
(1)
model pruning
(1)
entropy regularization
(1)
task distribution
(1)
progressive training
(1)
policy distillation
(1)
policy representation
(1)
action-space curriculum
(1)
Papers
Powerpropagation: A sparsity inducing weight reparameterisation
NIPS 2021
Top-KAST: Top-K Always Sparse Training
NIPS 2020
Stabilizing Transformers for Reinforcement Learning
ICML 2020
Distilling Policy Distillation
AISTATS 2019
Mix & Match Agent Curricula for Reinforcement Learning
ICML 2018
Been There, Done That: Meta-Learning with Episodic Recall
ICML 2018