Research map / Reinforcement learning / MDPs and planning
On the Challenges of Using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects
Sumana Basu, Marc-André Legault, Adriana Romero-Soriano, Doina Precup
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 |
|---|---|---|---|
| Augment the state with a decayed summary of prior insulin doses | DQN · Glucose control | cumulative discounted reward | Improved |
| Represent prolonged action effects with an effective-action state instead of recurrent action history | ADRQN · Glucose control | training runtime (mins/10K episode): 359.64 ± 19.25 -> 129.04 ± 42.73 | Improved |
| Represent prolonged action effects with an effective-action state instead of recurrent action history | ADRQN · Glucose control | maximum memory (MiB): 1623 -> 1513 | Improved |
| Augment the Q-learning state with effective action | Tabular Q-learning · MoveBlock | cumulative discounted return | Improved |
| Use a recurrent action-history policy rather than a Markov DQN | DQN · Glucose control | cumulative discounted reward | Improved |
| Use effective insulin-dose state information rather than recurrent action history | ADRQN · Glucose control | cumulative discounted reward | No clear effect |
| Use a Markov DQN that ignores prolonged action effects | Fixed Dose · Glucose control | cumulative discounted reward | Improved |
| Use a Markov DQN that ignores prolonged action effects | Effective-DQN · Glucose control | time in target blood glucose zone | Hurt |
Closest papers by meaning
- Quasi-optimal Reinforcement Learning with Continuous Actions (ICLR 2023 · similarity 0.86)
- EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes (NeurIPS 2024 · similarity 0.85)
- Position: Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination (ICML 2024 · similarity 0.83)
- When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL (NeurIPS 2024 · similarity 0.83)
- Model-based Reinforcement Learning for Confounded POMDPs (ICML 2024 · similarity 0.82)
- Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear MDPs (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.
