Research map / Reinforcement learning / MDPs and planning
Truncated Approximate Dynamic Programming with Task-Dependent Terminal Value
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 |
|---|---|---|---|
| increase number of training points for learning terminal value | TADP · Hybrid vehicle energy management | suboptimality ratio: within 1.5% of optimal at 8000 points, H=1 | Helped |
| use learned terminal value with H=1 instead of nominal policy | Nominal policy · Hybrid vehicle energy management | suboptimality ratio: ≈1.27 -> within 1.5% of optimal | Helped |
| increase planning horizon H with the same terminal value, no modeling error | TADP · Hybrid vehicle energy management | suboptimality ratio | Helped |
| increase planning horizon H under modeling error | TADP · Hybrid vehicle energy management (Delta in 0.3..0.8) | suboptimality ratio | Mixed |
| increase model uncertainty Delta (0 to 0.8) | TADP · Hybrid vehicle energy management | suboptimality ratio: Delta 0, 0.3, 0.6, 0.8 | Hurt |
| high uncertainty: use shortest horizon H=1 | TADP · Hybrid vehicle energy management (high Delta) | suboptimality ratio | Helped |
Closest papers by meaning
- Structure Matters: Dynamic Policy Gradient (NeurIPS 2025 · similarity 0.87)
- Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods (ICLR 2024 · similarity 0.87)
- Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs (NeurIPS 2026 · similarity 0.86)
- Planning and Learning in Average Risk-aware MDPs (NeurIPS 2025 · similarity 0.86)
- Rank-One Modified Value Iteration (ICML 2025 · similarity 0.85)
- Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes (AAAI 2024 · similarity 0.85)
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.