Rich Sutton

2 accepted papers

2026

Intentional Updates for Streaming Reinforcement Learning

Arsalan Sharifnassab, Mohamed Elsayed, Kris De Asis, Rupam Mahmood, Rich Sutton

ICML 2026poster

In gradient-based learning, a step size chosen in parameter units does not produce a predictable per-step change in the function output. This may lead to instability in the streaming setting (i.e., batch size=1), where stochasticity is not averaged out and update magnitudes can momentarily become ar…

Cited by 0 Source ↗Scholar ↗

2015

A Deeper Look at Planning as Learning from Replay

Harm Vanseijen, Rich Sutton

ICML 2015poster

In reinforcement learning, the notions of experience replay, and of planning as learning from replayed experience, have long been used to find good policies with minimal training data. Replay can be seen either as model-based reinforcement learning, where the store of past experiences serves as the…

Cited by 81 Source ↗PDF ↗code ↗Scholar ↗