RIC replaces single-pass label imitation with RL-driven iterative belief refinement, recovering cross-entropy optima while enabling adaptive halting via a value function.
Toward agents that reason about their computation.arXiv preprint arXiv:2510.22833
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Do Not Imitate, Reinforce: Iterative Classification via Belief Refinement
RIC replaces single-pass label imitation with RL-driven iterative belief refinement, recovering cross-entropy optima while enabling adaptive halting via a value function.
-
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.