method · first seen 13 Oct 2026
step-level reinforcement learning
Reinforcement learning assigning rewards and credit to individual decision steps within a multi-step trajectory.
Mentions per week
PapersCodeDiscussion
Earliest sources
- EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud DelegationPapers · 13 Oct 2026 · Zeru Shi, Jindong Jiang, Ryo Hachiuma, Yonggan Fu, Byung-Kwan Lee, Peter Belcak,…
Latest sources
- EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud DelegationPapers · 13 Oct 2026 · Zeru Shi, Jindong Jiang, Ryo Hachiuma, Yonggan Fu, Byung-Kwan Lee, Peter Belcak,…