AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

R-learning in actor-critic model offers a biologically relevant mechanism for sequential decision-making

Sergey Shuvaev, Sarah Starosta, Duda Kvitsiani, Adam Kepecs, Alexei Koulakov

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Stabilizing deep actor-critic · 6 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
R-learning instead of V-learning in actor-critic agentactor-critic model · random initial rewards taskleaving threshold depends on initial rewardImproved
R-learning instead of V-learningactor-critic model · fixed initial rewards task (12 or 18 µl)higher leaving threshold with larger initial rewardNo clear effect
Leaky MVT decision rule instead of MVTmouse behavior fit · random initial rewards, 7 miceDelta AIC: -67 ± 40Improved
R-learning instead of V-learning TD error as predictor of VTA dopamineactor-critic model · surprising rewards taskcorrelation with VTA DA: r = 0.52 and r = 0.51No clear effect
set exponential averaging constant kappa = 1 in V-learning (ablation)V-learning · random initial rewards taskleaving threshold vs initial rewardHurt

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