PapersSelected

Learning-Guided Planning in Large Dynamic Action Spaces

Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging

Why we picked it

This research provides a new method for learning-guided planning in large, dynamic action spaces, which could be relevant for applications like autonomous mobile charging stations.

The paper introduces LP-BTS, a learning-guided planning architecture for one-to-many mobile charging scenarios.

Body

It uses a graph proposal policy to concentrate candidate actions and a learned value critic to evaluate leaves.

In a 30-scenario bank, LP-BTS achieved the highest observed survival (0.4545) and alive-AUC (0.

8031).Its survival advantage over the strongest domain-engineered comparator was +0.

0066.

Original · arXiv cs.AI

Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging

Many learned sequential decision systems map the current state directly to an action. That shortcut becomes brittle when candidate actions are numerous, geometrically structured, and rebuilt with the state. One-to-many mobile charging makes this setting concrete: with N=250 sensors, the initial state induces about 1,125 candidate charging-stop actions; each chosen stop simultaneously serves its in-range sensors, and the action universe changes as sensors die. LP-BTS is a learning-guided planning architecture: a graph proposal policy concentrates a small candidate support, a learned value critic evaluates leaves, and edge-budgeted PUCT compares short simulated futures before committing an action. Because the policy scores this set without a fixed output head, a single frozen checkpoint covers every evaluated setting, spanning action universes from 736 to 2,813 stops. Matched ablations reveal complementary effects: uniform sampling costs 8.8 survival percentage points, while, with targeted support fixed, PUCT jointly retains 1.4 points (about 3.5 of 250 sensors) and direct policy selection travels 23% farther. On a prospectively specified, sealed 30-scenario confirmatory bank evaluated once, LP-BTS attains the highest observed survival (0.4545) and alive-AUC (0.8031). Its estimated survival advantage over the strongest domain-engineered comparator is +0.0066 (95% CI [-0.0037, +0.0184]), an unresolved difference, while it exceeds a deadline heuristic and two source-derived direct-policy reconstructions on every paired scenario. Both learned rows are trained, source-derived reconstructions of variants reported by Gong et al. In this setting, the results provide controlled evidence about learning-guided planning in a large, dynamic action space.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Learning-Guided Planning, Budgeted Tree Search.

Source attribution: curated from arXiv cs.AI (@Liang-Ching Tao, Pi-Chung Wang).