AI Paper Atlas

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

LPPG-RL: Lexicographically Projected Policy Gradient Reinforcement Learning with Subproblem Exploration

Ruiyu Qiu, Rui Wang, Guanghui Yang, Xiang Li, Zhijiang Shao

AAAI 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Policy gradients for special settings · 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
replace generic CVXPY solvers with Dykstra's projection for the gradient projection (ablation)LPPG-RL · Nav2D-1Gruntime (ms): 18.30 -> 0.93 (OSQP to Dykstra)Improved
replace generic CVXPY solvers with Dykstra's projection (ablation)LPPG-RL · Nav2D-100Gruntime (ms): OSQP 2907.73 vs Dykstra 2983.20No clear effect
replace generic CVXPY solvers with Dykstra's projection (ablation)LPPG-RL · Nav2D-nGfinal policy performanceNo clear effect
add Subproblem Exploration (uniform rollout scheduler over priority levels) (ablation)LPPG-PPO · Nav2D-2Glexicographic priority satisfied (K3 vs K4 return): K3 199 not completed -> 587 completedImproved
add Subproblem Exploration (ablation)LPPG-PPO · Nav2D-1Gsubtask completion: obstacle avoidance K2 -12 not completed -> 0 completedImproved
use projected gradient with SE instead of threshold-based LPALMORL baselines · Nav2D-2Gsubtask completionImproved
use projected gradient instead of Lagrangian-multiplier LPPOLMORL baselines · Nav2D-2Gsubtask completionImproved
LPPG-PPO gives lower K3 return than baselines on Nav2D-1G while satisfying constraintsLPPG-PPO · Nav2D-1GK3 return: LPPO 740 vs Ours 427Hurt

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