Learning neural-symbolic descriptive planning models via cube-space priors: The voyage home (to STRIPS)
We achieved a new milestone in the difficult task of enabling agents to learn about their
environment autonomously. Our neuro-symbolic architecture is trained end-to-end to …
environment autonomously. Our neuro-symbolic architecture is trained end-to-end to …
Classical planning in deep latent space
Current domain-independent, classical planners require symbolic models of the problem
domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile …
domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile …
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 …
decide which node to expand when multiple search nodes have the same evaluation score …
Capability construction of C4ISR based on AI planning
Z Jiao, P Yao, J Zhang, L Wan, X Wang - IEEE Access, 2019 - ieeexplore.ieee.org
This paper considers a capability construction problem of the C4ISR system under service-
oriented architecture. A capability construction model is first established and described in …
oriented architecture. A capability construction model is first established and described in …
Manipulation of articulated objects using dual-arm robots via answer set programming
The manipulation of articulated objects is of primary importance in Robotics and can be
considered as one of the most complex manipulation tasks. Traditionally, this problem has …
considered as one of the most complex manipulation tasks. Traditionally, this problem has …
Online macro generation for privacy preserving planning
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, often repeatedly develop similar paths. We describe a simple technique for online …
Planning with critical section macros: theory and practice
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 …
planning engines by providing “short-cuts” in the state space. Existing macro learning …
Neural-Symbolic Descriptive Action Model from Images: The Search for STRIPS
M Asai - arXiv preprint arXiv:1912.05492, 2019 - arxiv.org
Recent work on Neural-Symbolic systems that learn the discrete planning model from
images has opened a promising direction for expanding the scope of Automated Planning …
images has opened a promising direction for expanding the scope of Automated Planning …
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 …
component for intelligent autonomous agents. A cornerstone of domain-independent …
Outer entanglements: a general heuristic technique for improving the efficiency of planning algorithms
Domain independent planning engines accept a planning task description in a language
such as PDDL and return a solution plan. Performance of planning engines can be …
such as PDDL and return a solution plan. Performance of planning engines can be …