Research map / Architectures and efficiency / Neural architecture search
IRLAS: Inverse Reinforcement Learning for Architecture Search
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add mirror stimuli guidance to DARTS | DARTS · CIFAR-10 test | error (%): 2.83 -> 2.71 | Helped |
| Use IRLAS rather than the strongest listed baseline | CIFAR-10 architectures · CIFAR-10 test | error (%): 2.65 -> 2.60 | Helped |
| Add mirror stimuli guidance to BlockQNN or DARTS search | BlockQNN and DARTS · CIFAR-10 search | convergence speed | Helped |
| Add topological guidance during architecture search (ablation) | architecture search · ImageNet mobile | latency: about 1× faster | Helped |
| Set the topology-reward balance to λ=60 rather than λ=30 (ablation) | IRLAS · ImageNet mobile | accuracy | Hurt |
| Use fewer stacked blocks to make IRLAS-mobile-fast (ablation) | IRLAS-mobile · ImageNet mobile | latency: 12ms -> 9ms | Helped |
| Use fewer stacked blocks to make IRLAS-mobile-fast (ablation) | IRLAS-mobile · ImageNet mobile | top-1 accuracy (%): 75.28 -> 75.15 | Hurt |
Closest papers by meaning
- Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching (ICLR 2025 · similarity 0.85)
- Massively Scalable Inverse Reinforcement Learning in Google Maps (ICLR 2024 · similarity 0.85)
- Recent Advancements in Inverse Reinforcement Learning (AAAI 2024 · similarity 0.84)
- Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms (ICML 2024 · similarity 0.84)
- Inverse Reinforcement Learning by Estimating Expertise of Demonstrators (AAAI 2025 · similarity 0.84)
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.