Research map / Learning theory and algorithms / Prediction and decision losses
Safety Verification of Decision-Tree Policies in Continuous Time
Christian Schilling, Anna Lukina, Emir Demirović, Kim Guldstrand Larsen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| verify decision-tree policy directly instead of a neural-network policy | set-based reachability · Quadrotor | verification time: 10 and 59 minutes -> 6.5 minutes | Improved |
| exploit decision-tree structure instead of encoding as a general hybrid automaton | Ours vs JuliaReach · Cart-pole | analysis completion: 22 seconds | Improved |
| add fixpoint check after bisection | Algorithm 1 · Cart-pole | unbounded-time safety | Improved |
| ignore complement branch and skip bisection when leaves share an action | Algorithm 3 · hybrid-automaton comparison | precision and efficiency | Improved |
| subdivide initial set into smaller subsets | reachability analysis · Quadrotor | approximation error | Improved |
| handle state transformation before the tree (acrobot) | Algorithm 3 · Acrobot | verification time: 100 -> 112 | No clear effect |
| increase tree size from depth 2 to depth 3 policy | decision-tree policy · Acrobot | verification time: 101 sec -> 113 sec | Hurt |
| use DTCS larger tree (177 nodes) vs small trees | decision-tree policy · Quadrotor vs others | verification time: 84 sec | No clear effect |
Closest papers by meaning
- In Search of Trees: Decision-Tree Policy Synthesis for Black-Box Systems via Search (AAAI 2025 · similarity 0.89)
- Verified Safe Reinforcement Learning for Neural Network Dynamic Models (NeurIPS 2024 · similarity 0.84)
- SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes (NeurIPS 2025 · similarity 0.84)
- Explainably Safe Reinforcement Learning (NeurIPS 2025 · similarity 0.83)
- SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks (AAAI 2025 · similarity 0.83)
- Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization (ICLR 2025 · 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.
