Research map / Reinforcement learning / MDPs and planning
Classification with Costly Features Using Deep Reinforcement Learning
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 |
|---|---|---|---|
| Replace linear Q approximation (RL-lin) with neural network (RL-dqn) (ablation) | RL agent · all datasets except yeast and wine | cost-accuracy trade-off | Helped |
| Replace linear Q approximation with neural network (ablation) | RL agent · yeast and wine (small) | cost-accuracy trade-off | No clear effect |
| Add extensions (full RL agent) over RL-dqn (ablation) | RL agent · cifar, cifar-2, mnist | cost-accuracy trade-off | Helped |
| Remove advanced RL techniques (RL-dqn) (ablation) | RL agent · miniboone convergence | convergence speed | Hurt |
| Add pretraining (ablation) | RL agent · miniboone convergence | convergence speed | Helped |
| Remove the external classifier (RL-nohpc) (ablation) | RL agent · forest-2 | cost-accuracy trade-off | Helped |
| Use non-predictive random HPC (RL-fakehpc) (ablation) | RL agent · forest-2 | cost-accuracy trade-off | Mixed |
| Full RL agent versus Adapt-Gbrt and BudgetPrune | RL agent · miniboone, forest, cifar, mnist | cost-accuracy trade-off | Helped |
| Full RL agent versus prior art | RL agent · cifar-2 and forest-2 | cost-accuracy trade-off | Mixed |
Closest papers by meaning
- Linear Feature Encoding for Reinforcement Learning (NeurIPS 2016 · similarity 0.87)
- Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning (ICLR 2025 · similarity 0.86)
- Cost-Aware Learning (NeurIPS 2026 · similarity 0.85)
- Stochastic Q-learning for Large Discrete Action Spaces (ICML 2024 · similarity 0.84)
- Stop Regressing: Training Value Functions via Classification for Scalable Deep RL (ICML 2024 · similarity 0.84)
- Confounding Robust Deep Reinforcement Learning: A Causal Approach (NeurIPS 2025 · 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.