AI Paper Atlas

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

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels

Siow Meng Low, Ze Gong, Akshat Kumar

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Safety layers and shielding · 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 TraCeS per-timestep credit instead of the C-T MLP estimatorPPO-Lagrangian · PointCircle1labeled trajectories: 12000 -> 5830 (918)Improved
use TraCeS instead of C-TPPO-Lagrangian · Hoppercost: 284.2 (289.2) -> 17.1 (4.7)Improved
use TraCeS instead of C-TPPO-Lagrangian · HalfCheetahcost: 99.7 (74.5) -> 22.4 (5.3)Improved
use TraCeS instead of C-TPPO-Lagrangian · CarCircle2cost: 44.0 (24.0) -> 11.9 (10.0)Improved
use TraCeS instead of C-TPPO-Lagrangian · Antlabeled trajectories: 6000 (0) -> 4657 (551)Improved
use TraCeS instead of C-TPPO-Lagrangian · Walker2dcost: 16.7 (9.1) -> 24.1 (3.9)Hurt
use TraCeS instead of partial-knowledge RLSFPPO-Lagrangian · Walker2dlabeled trajectories: 15227 (1920) -> 5735 (1041)Improved
use TraCeS instead of partial-knowledge RLSFPPO-Lagrangian · PointCircle1cost: 1.6 (2.2) -> 16.2 (7.2)Hurt
use TraCeS instead of RLSFPPO-Lagrangian · CarCircle1cost: 33.8 (41.7) -> 11.3 (8.0)Improved

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