Somjit Nath
4 papers · 2019–2023 · 3 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(10)
๐ฃ
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
temporal difference learning
(2)
representation learning
(1)
reinforcement learning
(1)
policy evaluation
(1)
online learning
(1)
neural network optimization
(1)
value function
(1)
value function approximation
(1)
state representation learning
(1)
recurrent neural network
(1)
fast adaptation
(1)
general value function
(1)
training loss
(1)
object-centric representation
(1)
experience replay
(1)
nonlinear function approximation
(1)
sample prioritization
(1)
steady decrease
(1)
backprop through time
(1)
reducible loss
(1)
Papers
Discovering Object-Centric Generalized Value Functions From Pixels
ICML 2023
Prioritizing Samples in Reinforcement Learning with Reducible Loss
NeurIPS 2023
Training Recurrent Neural Networks Online by Learning Explicit State Variables
ICLR 2020
Two-Timescale Networks for Nonlinear Value Function Approximation
ICLR 2019