Author

Everest Yang

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Characterizing Replay Retention Under Dynamics Shift in Model-Based Reinforcement Learning

The results show that replay retention depends on change magnitude and on how the dynamics evolve, and an estimator built from interaction data can still provide the quantities needed to choose a replay strategy after permanent changes.

Everest Yang, Skye Thompson, G. Konidaris · 0 citations

#machine learning Preprint Jul 2026

Changepoint-Aware World Models: Detecting Dynamics Shifts and Recovering by Forgetting Stale Replay in Model-Based RL

CAWM is presented, a DreamerV3 agent that detects an abrupt dynamics shift from its own internal prediction error, using an online CUSUM test against a rolling baseline that fires only on abrupt change rather than on slow learning drift, and recovers substantially faster than passive retraining.

Everest Yang · 0 citations