AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms

Ezgi Korkmaz

AAAI 2026 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 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
use plain Dueling instead of higher-capacity distributional C51C51 · ALE 100Khuman normalized median: 0.0941 -> 0.2304Improved
use plain Dueling instead of QR-DQNQR-DQN · ALE 100Khuman normalized median: 0.0820 -> 0.2304Improved
use plain Dueling instead of IQNIQN · ALE 100Khuman normalized median: 0.0528 -> 0.2304Improved
use plain Dueling instead of Double-QDouble-Q · ALE 100Khuman normalized mean: 0.3169 -> 0.2923Hurt
use plain Dueling instead of PriorPrior · ALE 100K20th percentile: 0.0267 -> 0.0764Improved
compare DrQ (ICLR) against core Dueling baseline rather than DERDrQ (ICLR) · ALE 100Kperformance gain over baseline: 82% -> 11%No clear effect
compare DrQ (NeurIPS reimplementation) to DuelingDueling · ALE 100Kperformance: 15% betterHurt

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