SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning
SERO trains long-horizon agents using executable oracle continuations and reachability weighting on ALFWorld and WebShop.
1 stories, newest first · one card per story
SERO trains long-horizon agents using executable oracle continuations and reachability weighting on ALFWorld and WebShop.
Today 2.3K readers · 2.8K views · 411 reads · all time 108K views