Classical planning in deep latent space: Bridging the subsymbolic-symbolic boundary

M Asai, A Fukunaga - Proceedings of the aaai conference on artificial …, 2018 - ojs.aaai.org
Current domain-independent, classical planners require symbolic models of the problem
domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile …

Reinforcement learning for classical planning: Viewing heuristics as dense reward generators

C Gehring, M Asai, R Chitnis, T Silver… - Proceedings of the …, 2022 - ojs.aaai.org
Recent advances in reinforcement learning (RL) have led to a growing interest in applying
RL to classical planning domains or applying classical planning methods to some complex …

Tie-breaking strategies for cost-optimal best first search

M Asai, A Fukunaga - Journal of Artificial Intelligence Research, 2017 - jair.org
Best-first search algorithms such as A* need to apply tie-breaking strategies in order to
decide which node to expand when multiple search nodes have the same evaluation score …

Improving domain-independent planning via critical section macro-operators

L Chrpa, M Vallati - Proceedings of the AAAI Conference on Artificial …, 2019 - aaai.org
Macro-operators, macros for short, are a well-known technique for enhancing performance
of planning engines by providing “short-cuts” in the state space. Existing macro learning …

Composing Synergistic Macro Actions for Reinforcement Learning Agents

YM Chen, KY Chang, C Liu, TC Hsiao… - … on Neural Networks …, 2022 - ieeexplore.ieee.org
Macro actions have been demonstrated to be beneficial for the learning processes of an
agent and have encouraged a variety of techniques to be developed for constructing more …

Online macro generation for privacy preserving planning

S Maliah, G Shani, R Brafman - Proceedings of the International …, 2016 - ojs.aaai.org
Abstract Agents that use Multi-Agent Forward Search (MAFS) todo privacy-preserving
planning, often repeatedly develop similar paths. We describe a simple technique for online …

Planning with critical section macros: theory and practice

L Chrpa, M Vallati - Journal of Artificial Intelligence Research, 2022 - jair.org
Macro-operators (macros) are a well-known technique for enhancing performance of
planning engines by providing “short-cuts” in the state space. Existing macro learning …

Reformulation techniques for automated planning: a systematic review

D Alarnaouti, G Baryannis, M Vallati - The Knowledge Engineering …, 2023 - cambridge.org
Automated planning is a prominent area of Artificial Intelligence and an important
component for intelligent autonomous agents. A cornerstone of domain-independent …

Efficient black-box planning using macro-actions with focused effects

C Allen, M Katz, T Klinger, G Konidaris… - arXiv preprint arXiv …, 2020 - arxiv.org
The difficulty of deterministic planning increases exponentially with search-tree depth. Black-
box planning presents an even greater challenge, since planners must operate without an …

[PDF][PDF] Recursive Agents and Landmarks Strategic-Tactical Planning (RALSTP)

D Buksz - 2024 - kclpure.kcl.ac.uk
The use of AI planning beyond demonstration examples has proven to be challenging for
expressive problems with numerous components. This happens primarily because the state …