Knowledge Graph

Graph explorer

Search resolved entities, walk their edges, and read the sentence behind every one.

Entities25 of 207,987

Entity

Horizon Adaptive Offline Policy Learning via Value Stitching

technology1 mentionslast seen Oct 14, 2026

A method that replaces fixed-horizon backups with recursive, horizon-adaptive value composition for offline reinforcement learning.

Relationships 5

Horizon Adaptive Offline Policy Learning via Value Stitchingapplies tooffline reinforcement learning85% confidence1 source
Horizon Adaptive Offline Policy Learning via Value Stitchingapplies tolong-horizon decision-making85% confidence1 source
Horizon Adaptive Offline Policy Learning via Value Stitchingcompetes withn-step TD backup80% confidence1 source
Horizon Adaptive Offline Policy Learning via Value Stitchingcompetes withgenerative-value offline RL80% confidence1 source
Horizon Adaptive Offline Policy Learning via Value Stitchingdepends ontemporal difference learning75% confidence1 source

Horizon Adaptive Offline Policy Learning via Value Stitching

Relationship

Horizon Adaptive Offline Policy Learning via Value Stitchingapplies tooffline reinforcement learning

85% confidence1 supporting mentions

Either name opens that entity’s relationships.

Sources 1

preprintarXivOct 11, 2026Horizon Adaptive Offline Policy Learning via Value Stitching
Learning accurate value functions plays a decisive role for reinforcement learning (RL) agents to solve long-horizon, complex tasks