Shantanu Thakoor
8 papers · 2021–2023 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
๐ Conference Polyglot (3) ๐ Interdisciplinary Bridge ๐งญ Keyword Pioneer ๐ฃ Hot Topic Early Bird ๐ Cross-Pollinator (14)
๐บ๏ธ
Taxonomy Completionist
(16)
๐
Triple Crown
Conferences
ICML (5)
NIPS (2)
ICLR (1)
Top co-authors
Research topics
Keywords
representation learning
(3)
self-supervised learning
(3)
multi-task learning
(1)
transfer learning
(1)
policy gradient
(1)
behavior analysis
(1)
message passing
(1)
value function
(1)
value iteration
(1)
model-based reinforcement learning
(1)
singular value decomposition
(1)
variance reduction
(1)
policy improvement
(1)
action prediction
(1)
curiosity-driven learning
(1)
spectral decomposition
(1)
latent representation
(1)
prediction error
(1)
world model
(1)
counterfactual reasoning
(1)
Papers
Relax, it doesnโt matter how you get there: A new self-supervised approach for multi-timescale behavior analysis
NIPS 2023
Half-Hop: A graph upsampling approach for slowing down message passing
ICML 2023
Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition
ICML 2023
Understanding Self-Predictive Learning for Reinforcement Learning
ICML 2023
Generalised Policy Improvement with Geometric Policy Composition
ICML 2022
Large-Scale Representation Learning on Graphs via Bootstrapping
ICLR 2022
BYOL-Explore: Exploration by Bootstrapped Prediction
NIPS 2022
Counterfactual Credit Assignment in Model-Free Reinforcement Learning
ICML 2021