Research map / Reinforcement learning / MDPs and planning
Budgeted Reinforcement Learning in Continuous State Space
Nicolas Carrara, Edouard Leurent, Romain Laroche, Tanguy Urvoy, Odalric-Ambrym Maillard, Olivier Pietquin
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 |
|---|---|---|---|
| Use risk-sensitive exploration that samples initial budgets uniformly and keeps sampled trajectories within feasible budgets, rather than risk-neutral ε-greedy exploration | BFTQ on Corridors · Corridors | reward-cost trade-off performance across budgets | Improved |
| Use BFTQ instead of FTQ with Lagrangian relaxation | BFTQ · Slot-filling | reward-cost trade-off performance | No clear effect |
| Use BFTQ instead of FTQ with Lagrangian relaxation | BFTQ · highway-env | reward-cost trade-off performance | No clear effect |
| Use BFTQ instead of FTQ with Lagrangian relaxation | BFTQ · Slot-filling and highway-env | expected cost control | Improved |
| Use BFTQ instead of FTQ with Lagrangian relaxation | BFTQ · Slot-filling and highway-env | extra-seed variance | Improved |
| Use BFTQ at budget β=0 | BFTQ · highway-env | expected cost: ≃ 0.1 | Hurt |
Closest papers by meaning
- Semi-Infinitely Constrained Markov Decision Processes and Provably Efficient Reinforcement Learning (TPAMI 2024 · similarity 0.86)
- POMDPs in Continuous Time and Discrete Spaces (NeurIPS 2020 · similarity 0.86)
- Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs (NeurIPS 2024 · similarity 0.85)
- Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces (NeurIPS 2024 · similarity 0.85)
- Near-Optimal Sample Complexity for Online Constrained MDPs (NeurIPS 2025 · similarity 0.85)
- SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes (NeurIPS 2025 · 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.
