Short-to-Long: Detached Features for Long-Horizon Value Learning
arXiv:2610.30461v1 Announce Type: new Abstract: Learning useful representations from continually changing value targets remains a challenge in deep reinforcement learning. We study the temporal horizon of this supervision: smaller discounts make these targets less sensitive to distant bootstrap cha…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-23 04:00 · arXiv cs.LG
Short-to-Long: Detached Features for Long-Horizon Value Learning