AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Dynamic Control of Stochastic Evolution: A Deep Reinforcement Learning Approach to Adaptively Targeting Emergent Drug Resistance

Dalit Engelhardt

JMLR 2020 · Reinforcement learning › Visual and representation RL · approach: Skill learning and diffusion policies · 12 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
train with 0.3 per-episode probability of mutation instead of mutations allowed in every episode with lower or higher per-step rate (ablation)CelluDose DDPG training · training performance (drug resistance simulation)training performance: P_epis,mut=0.3 vs P_epis,mut=1 with P_step,mut=0.3 times PhiImproved
add the model-derived instantaneous growth rate as a state feature and shaping potentialCelluDose DDPG · training convergencepolicy learningImproved
add 20-fold lower mid-episode dosage penalty when population exceeds initial population (binary penalty function) (ablation)CelluDose reward · training stabilitystability and sensitivity to penalty weights: 20-fold lower weightImproved
add positive bias initialization of the actor/critic from deterministic dose estimate (ablation)CelluDose networks · trainingavoids zero-dose local optimumImproved
add an extra hidden layer to the actor network (ablation)DDPG actor · trainingperformanceImproved
rescale cell concentrations by log(x+1)/log(K) (ablation)CelluDose state features · trainingconvergence smoothnessImproved
raise mutation probability above the training value of 1e-6 up to 1e-3 for dual-drug policyCelluDose dual-drug policy · mutation-rate robustnesssuccess rate: 100% success up to P_step,mut=10^-3No clear effect
raise mutation probability to 1e-2 for dual-drug policyCelluDose dual-drug policy · mutation-rate robustnesssuccess rate: 100% -> 47% success at P_step,mut=10^-2Hurt
raise mutation probability up to 1e-1 for single-drug policyCelluDose single-drug policy · mutation-rate robustnesssuccess rate: 100% success up to P_step,mut=10^-1No clear effect
use wider hidden layers and more samples for dual-drug instead of single-drug trainingCelluDose · dual-drug trainingepisodes to convergence: 50,000 -> 130,000 episodesMixed

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