AI Paper Atlas

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

Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access

Daniel Ebi, Damien Ernst, Klemens Böhm, Gaspard Lambrechts

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Actor-critic theory

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
use informed critic with signal [s1,s2,s4,s5] instead of symmetric history criticinformed-asym-A2C · Synthetic informed POMDP (|S|=20, 5 state features)AUC of mean episodic return: 1.06 x 10^{5} -> 1.23e+05Improved
add reward-relevant features s4 and s5 to the privileged signal [s1,s2] (ablation)informed-asym-A2C · Synthetic informed POMDP (|S|=20, 5 state features)AUC of mean episodic return: 1.07e+05 -> 1.23e+05Improved
add s3 (redundant feature) to the signal [s1,s2,s4,s5] (ablation)informed-asym-A2C · Synthetic informed POMDP (|S|=20, 5 state features)AUC of mean episodic return: 1.23e+05 -> 1.19e+05Hurt
add s3 to the signal [s1,s2,s4,s5] (ablation)informed-asym-A2C · Synthetic informed POMDP (|S|=20, 5 state features)Prediction informativeness L_tau: 0.064 -> 0.056Hurt
add s3 to the signal [s1,s2,s4,s5] (ablation)informed-asym-A2C · Synthetic informed POMDP (|S|=20, 5 state features)Residual informativeness p-value: 0.035 -> 0.038Hurt
add s3 to the signal [s1,s2] (ablation)informed-asym-A2C · Synthetic informed POMDP (|S|=20, 5 state features)AUC of mean episodic return: 1.07e+05 -> 1.08e+05No clear effect
add s4 to the signal [s1,s2] (ablation)informed-asym-A2C · Synthetic informed POMDP (|S|=20, 5 state features)Prediction informativeness p-value: 0.801 -> 0.043Improved
add s5 to the signal [s1,s2] (ablation)informed-asym-A2C · Synthetic informed POMDP (|S|=20, 5 state features)AUC of mean episodic return: 1.07e+05 -> 1.10e+05No clear effect
add s4 to the signal [s1,s2,s3] (ablation)informed-asym-A2C · Synthetic informed POMDP (|S|=20, 5 state features)Residual informativeness p-value: 0.170 -> 0.068Improved
add s5 to the signal [s1,s2,s4] (ablation)informed-asym-A2C · Synthetic informed POMDP (|S|=20, 5 state features)AUC of mean episodic return: 1.08e+05 -> 1.23e+05Improved
use informed partial-signal critic instead of full-state history-state criticinformed-asym-A2C · POPGym Concentrationepisodic return (Concentration)Improved
use informed critic instead of symmetric A2C on Position Cart Poleinformed-asym-A2C · POPGym Position Cart Poleepisodic return (Position Cart Pole)Improved

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