Somjit Nath
4 papers · 2019–2023 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
ICLR (2)
ICML (1)
NIPS (1)
Top co-authors
Keywords
deep reinforcement learning
(1)
representation learning
(1)
reinforcement learning
(1)
temporal difference learning
(1)
value function
(1)
fast adaptation
(1)
general value function
(1)
training loss
(1)
object-centric representation
(1)
experience replay
(1)
sample prioritization
(1)
steady decrease
(1)
reducible loss
(1)
Papers
Prioritizing Samples in Reinforcement Learning with Reducible Loss
NIPS 2023
Discovering Object-Centric Generalized Value Functions From Pixels
ICML 2023
Training Recurrent Neural Networks Online by Learning Explicit State Variables
ICLR 2020
Two-Timescale Networks for Nonlinear Value Function Approximation
ICLR 2019