AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

EA: Managing Green Data Centers Using Deep Reinforcement Learning Without Discounting

Peijian Wang, Thu Nguyen

AAAI 2026 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments

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
apply the EA framework (finite-horizon approximation, stationary policy) instead of GreenDRLPPO green DC agent · Green DC simulator (old simulator)reward: -103.7 -> −82.7Improved
use EA instead of PEBPPO green DC agent · Green DC simulator (new simulator)reward: −97.9 -> −84.6Improved
use EA instead of APO (average-reward)PPO green DC agent · Green DC simulator (new simulator)reward: −117.4 -> −84.6Improved
lengthen episode from 0.5-1 day to at least 1.5 days (ablation)EA · Green DC simulatorreward: −7506.3 -> −89.0 (1.5 days); −84.6 at 3 daysImproved
keep repeating pattern in short episodes (vs. long episode without repeating pattern) (ablation)EA · Synthetic tracesreward: (−3.4 ± 2.3) × 105 -> −103.3 (2h deadline)Improved
lengthen deferrable deadline from 2 to 4 hours (ablation)EA with repeating pattern · Synthetic tracesreward: −103.3 -> −85.7Improved
use total episode reward instead of reward-to-go as advantage (no baseline) (ablation)EA · Green DC simulatorreward: −117.2 -> −86.1Improved
add input-dependent baseline to reward-to-go (ablation)EA · Green DC simulatorreward: −117.2 -> −85.9Improved
add input-dependent baseline to total episode reward (ablation)EA · Green DC simulatorreward: −86.1 -> −84.6Improved
add state-value baseline to total episode reward (ablation)EA · Green DC simulatorreward: −86.1 -> −87.2No clear effect
use GreenDRL inputs and actions with EA framework (Mixed) vs full EA (ablation)EA · Green DC simulator (old simulator)reward: −84.9 -> −82.7No 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