Pith. sign in

Distributional reinforcement learning with quantile regression

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Pessimistic Risk-Aware Policy Learning in Contextual Bandits

stat.ML · 2026-05-15 · unverdicted · novelty 6.0

A distributional framework for optimizing Lipschitz risk functionals in offline contextual bandits yields data-dependent suboptimality bounds of Õ(1/√n) that match risk-neutral rates and are minimax optimal.

Revisiting Adam for Streaming Reinforcement Learning

cs.LG · 2026-05-07 · unverdicted · novelty 5.0

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

Showing 2 of 2 citing papers.

  • Pessimistic Risk-Aware Policy Learning in Contextual Bandits stat.ML · 2026-05-15 · unverdicted · none · ref 11

    A distributional framework for optimizing Lipschitz risk functionals in offline contextual bandits yields data-dependent suboptimality bounds of Õ(1/√n) that match risk-neutral rates and are minimax optimal.

  • Revisiting Adam for Streaming Reinforcement Learning cs.LG · 2026-05-07 · unverdicted · none · ref 9

    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.