AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Reinforcement Learning for Joint Optimization of Multiple Rewards

Mridul Agarwal, Vaneet Aggarwal

JMLR 2023 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs

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 proposed model-based or model-free multi-objective algorithm instead of DQN baselineCellular scheduling with proportional fairness · Proportional fairness, K=2,4,6 usersfairness utility f_tImproved
use proposed model-based algorithm instead of Blind Gradient EstimationCellular scheduling with proportional fairness · Proportional fairness, K=2 usersfairness utility f_tImproved
use proposed model-based algorithm instead of Blind Gradient EstimationCellular scheduling with proportional fairness · Proportional fairness, K=4 and 6 users (finite horizon)fairness utility f_tHurt
use proposed model-free algorithm instead of standard policy gradient with fairness-so-far rewardCellular scheduling · Alpha=2 fairness, K=8 users, Gauss-Markov channelfairness utility f_tImproved
use fairness value as reward for policy gradient (linear approximation) as the number of users growsVanilla policy gradient · Proportional fairness K=2 vs alpha=2 fairnessfairness utility f_tHurt

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