Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Verification of RNN-Based Neural Agent-Environment Systems
Read the paperCheck 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 |
|---|---|---|---|
| use Input on Demand unrolling instead of Input on Start (ablation) | RNSVerify · Pendulum-v0, X^8(theta_f > -pi/10) | MILP solve time: 693.2s -> 0.689s | Helped |
| use Input on Demand unrolling instead of Input on Start (ablation) | RNSVerify · Pendulum-v0, X^7(theta_f > -pi/70) | MILP solve time: 207.8s -> 0.478s | Helped |
| use Input on Demand unrolling instead of Input on Start (ablation) | RNSVerify · Pendulum-v0 n=8 | MILP variables: 11130 -> 4970 | Helped |
| use Input on Demand unrolling instead of Input on Start (ablation) | RNSVerify · Pendulum-v0 n=8 | MILP constraints: 13881 -> 6181 | Helped |
| use Input on Demand unrolling instead of Input on Start (ablation) | RNSVerify · Pendulum-v0, n=1 with small eps | MILP solve time: 0.014s vs 0.014s | No clear effect |
Closest papers by meaning
- Training Verification-Friendly Neural Networks via Neuron Behavior Consistency (AAAI 2025 · similarity 0.84)
- Real-Time Recurrent Learning using Trace Units in Reinforcement Learning (NeurIPS 2024 · similarity 0.83)
- Efficient Verification of ReLU-Based Neural Networks via Dependency Analysis (AAAI 2020 · similarity 0.83)
- Provably Safe Neural Network Controllers via Differential Dynamic Logic (NeurIPS 2024 · similarity 0.83)
- Neural Interactive Proofs (ICLR 2025 · similarity 0.83)
- Logical characterizations of recurrent graph neural networks with reals and floats (NeurIPS 2024 · similarity 0.82)
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.
