AI Paper Atlas

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

Mirror Descent Actor Critic via Bounded Advantage Learning

Ryo Iwaki

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Off-policy actor-critic with expressive policies · 0 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
bound the current-state log-policy term in the critic loss (replace identity with tanh(x/10)) (ablation)MDAC · Mujoco (6 environments)baseline-normalized IQM scoreImproved
bound the successor-state log-policy term in addition to the current one (ablation)MDAC · Mujoco (6 environments)baseline-normalized IQM scoreImproved
bound only the successor term while leaving current term as identity (ablation)MDAC · Mujoco (6 environments)baseline-normalized IQM scoreHurt
use slower-saturating clip(x/10,-1,1) or tanh(x/10) instead of clip(x,-1,1) or tanh(x) (ablation)MDAC · Mujoco (6 environments)baseline-normalized IQM scoreImproved
use tanh instead of clip as bounding function (ablation)MDAC · Mujoco (6 environments)baseline-normalized IQM scoreNo clear effect
use sign(x) as bounding function instead of clip or tanh (ablation)MDAC · Mujoco (6 environments)baseline-normalized IQM scoreHurt
use time-dependent successor bounding that approaches identity (ablation)MDAC · Mujoco (6 environments)baseline-normalized IQM scoreImproved
vary T1 of time-dependent bounding over 1e5 to 1e6 (ablation)MDAC · Mujoco (6 environments)baseline-normalized IQM scoreNo clear effect
use MDAC instead of TD3, SAC and X-SACMDAC · Mujoco (6 environments)baseline-normalized IQM scoreImproved
use X-SAC instead of SACX-SAC · Mujoco (6 environments)baseline-normalized IQM scoreHurt
use MDAC instead of SACMDAC · Adroit and DMC dogaggregated normalized IQM scoreImproved
use MDAC instead of SACMDAC · AdroitHandDoor-v1returnNo clear effect

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