AI Paper Atlas

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

AAAI 2023 · Reinforcement learning › MDPs and planning · approach: POMDPs and confounded RL · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
Augment the state with a decayed summary of prior insulin dosesDQN · Glucose controlcumulative discounted rewardImproved
Represent prolonged action effects with an effective-action state instead of recurrent action historyADRQN · Glucose controltraining runtime (mins/10K episode): 359.64 ± 19.25 -> 129.04 ± 42.73Improved
Represent prolonged action effects with an effective-action state instead of recurrent action historyADRQN · Glucose controlmaximum memory (MiB): 1623 -> 1513Improved
Augment the Q-learning state with effective actionTabular Q-learning · MoveBlockcumulative discounted returnImproved
Use a recurrent action-history policy rather than a Markov DQNDQN · Glucose controlcumulative discounted rewardImproved
Use effective insulin-dose state information rather than recurrent action historyADRQN · Glucose controlcumulative discounted rewardNo clear effect
Use a Markov DQN that ignores prolonged action effectsFixed Dose · Glucose controlcumulative discounted rewardImproved
Use a Markov DQN that ignores prolonged action effectsEffective-DQN · Glucose controltime in target blood glucose zoneHurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy