Yuhuai Wu, Łukasz Kuci, Piotr Miłoś, Konrad Czechowski, Tomasz Odrzygóźdź, Marek Zbysi, Michał Zawalski, Krzysztof Olejnik
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propose Subgoal Search (kSubS) method. Its key component is a learned subgoal generator that produces a diversity of subgoals that are both achievable and closer to the solution. Using subgoals reduces the search space and induces a high-level search graph suitable for efficient planning. In this paper, we implement kSubS using a transformerbased subgoal module coupled with the classical best-first search framework. We show that a simple approach of generating k-th step ahead subgoals is surprisingly efficient on three challenging domains: two popular puzzle games, Sokoban and the Rubik's Cube, and an inequality proving benchmark INT. kSubS achieves strong results including state-of-the-art on INT within a modest computational budget.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2108.11204")
get_code_for_paper("2108.11204")
have("2108.11204")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2108.11204.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2108.11204)
Connect an agent — have() is free.