AI Paper Atlas

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

Implicit Distributional Reinforcement Learning

Yuguang Yue, Zhendong Wang, Mingyuan Zhou

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Actor-critic theory · 7 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
IDAC vs SACIDAC · Walker2dmax average return: 4328.95 -> 5107.07Improved
IDAC vs SACIDAC · HalfCheetahmax average return: 10626.34 -> 12222.80Improved
IDAC vs SACIDAC · Antmax average return: 3732.23 -> 4930.73Improved
IDAC vs TD3IDAC · Antmax average return: 4905.74 -> 4930.73No clear effect
IDAC vs SACIDAC · Humanoidmax average return: 5055.64 -> 5233.43Improved
replace Gaussian policy with semi-implicit policy (ablation)IDAC-Gaussian · HalfCheetah, Walker2d, Anttraining curvesImproved
use implicit policy without tractable entropy instead of semi-implicit (ablation)IDAC · HalfCheetah, Walker2d, Anttraining curvesHurt
replace action-value critic with distributional DGN critic (ablation)SAC (IDAC-Gaussian vs SAC) · HalfCheetah, Walker2d, Anttraining curvesImproved
twin-delayed instead of single DGN critic (ablation)IDAC-Single · HalfCheetah, Walker2d, Anttraining curvesImproved
twin-delayed instead of single critic (ablation)SDPG · HalfCheetah, Walker2d, Anttraining curvesImproved
estimate objective with J sampled actions (ablation)SAC (SAC-J) · HalfCheetah, Walker2d, Anttraining curvesNo clear effect
make J, K, L too smallIDAC · some tasksperformanceHurt

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