method · first seen 14 Oct 2026
action masking
Also: action mask, masked actions, invalid action masking
Restricting an agent's choices to valid actions, where the validity mask must itself be discovered during learning.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Deep Reinforcement Learning for HPC Job Scheduling: A Statistical EvaluationPapers · 14 Oct 2026 · Justin M. Cheney, Clement N. Nyirenda
- LangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial OptimizationPapers · 16 Oct 2026 · Hironori Ohigashi
- Confessions of a Masked MDPPapers · 20 Oct 2026 · Sebastian Reboul, Lorenzo Croissant, Hélène Halconruy
- A physics-constrained deep reinforcement learning method for autonomous mission planning of Titan deep space probesPapers · 11 Nov 2026 · Hanmin Li, Tao Wang, Shuangliang Liu, Zhe Zhang, Maodeng Li
Latest sources
- A physics-constrained deep reinforcement learning method for autonomous mission planning of Titan deep space probesPapers · 11 Nov 2026 · Hanmin Li, Tao Wang, Shuangliang Liu, Zhe Zhang, Maodeng Li
- Confessions of a Masked MDPPapers · 20 Oct 2026 · Sebastian Reboul, Lorenzo Croissant, Hélène Halconruy
- LangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial OptimizationPapers · 16 Oct 2026 · Hironori Ohigashi
- Deep Reinforcement Learning for HPC Job Scheduling: A Statistical EvaluationPapers · 14 Oct 2026 · Justin M. Cheney, Clement N. Nyirenda