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 …
Improving domain-independent planning via critical section macro-operators
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 …
of planning engines by providing “short-cuts” in the state space. Existing macro learning …
Continuing plan quality optimisation
FH Siddiqui, P Haslum - Journal of Artificial Intelligence Research, 2015 - jair.org
Finding high quality plans for large planning problems is hard. Although some current
anytime planners are often able to improve plans quickly, they tend to reach a limit at which …
anytime planners are often able to improve plans quickly, they tend to reach a limit at which …
Plan deordering with conditional effects
SB Noor, FH Siddiqui - Proceedings of SAI Intelligent Systems Conference, 2022 - Springer
Plan deordering aids several tasks such as plan reuse, modification, and plan
decomposition by preserving only the necessary orderings among the actions in a plan …
decomposition by preserving only the necessary orderings among the actions in a plan …
Revisiting block deordering in finite-domain state variable planning
SB Noor, FH Siddiqui - AI Communications, 2024 - content.iospress.com
Plan deordering removes unnecessary ordering constraints between actions in a plan,
facilitating plan execution flexibility and several other tasks, such as plan reuse …
facilitating plan execution flexibility and several other tasks, such as plan reuse …
Improving Plan Execution Flexibility using Block-Substitution
SB Noor, FH Siddiqui - arXiv preprint arXiv:2406.03091, 2024 - arxiv.org
Partial-order plans in AI planning facilitate execution flexibility due to their less-constrained
nature. Maximizing plan flexibility has been studied through the notions of plan deordering …
nature. Maximizing plan flexibility has been studied through the notions of plan deordering …
Inner entanglements: Narrowing the search in classical planning by problem reformulation
In the field of automated planning, the central research focus is on domain‐independent
planning engines that accept planning tasks (domain models and problem descriptions) in a …
planning engines that accept planning tasks (domain models and problem descriptions) in a …
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 …
Macro operator synthesis for adl domains
A macro operator is a planning operator that is generated from a sequence of actions.
Macros have mostly been used for macro planning, where the planner considers the macro …
Macros have mostly been used for macro planning, where the planner considers the macro …