C51 matches StreamQ in streaming RL on 55 Atari games while a new Adaptive Q(λ) algorithm based on bounded derivatives and variance-adjusted updates reaches nearly double the human baseline.
Rusu and Joel Veness and Marc G
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Revisiting Adam for Streaming Reinforcement Learning
C51 matches StreamQ in streaming RL on 55 Atari games while a new Adaptive Q(λ) algorithm based on bounded derivatives and variance-adjusted updates reaches nearly double the human baseline.