AI Paper Atlas

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

Accelerated Learning with Linear Temporal Logic using Differentiable Simulation

Alper Kamil Bozkurt, Calin Belta, Ming Lin

ICLR 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Constrained policy optimization · 1 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 differentiable LTL rewards instead of discrete LTL rewards (ablation)SHAC/AHAC · CartPole, Hopper, Cheetah, Ant LTL tasksLTL satisfaction probabilityImproved
use differentiable-simulator RL (SHAC/AHAC) with differentiable LTL rewards vs PPO/SACSHAC/AHAC vs PPO/SAC · CartPoleLTL satisfaction probability: near-optimal (Pr>0.8) within 20 M steps vs no meaningful reward after 100 MImproved
use differentiable RL with differentiable LTL rewards vs PPO/SACSHAC/AHAC vs PPO/SAC · Hoppersteps to near-optimal: 20 M vs 100 M stepsImproved
use differentiable RL with differentiable LTL rewards vs PPO/SACSHAC/AHAC vs PPO/SAC · Cheetah and AntLTL satisfaction probabilityImproved
simplify the LTL formula (reachability only) (ablation)PPO/SAC · CartPole and legged robotsLTL satisfaction probability: to Pr>0.9Improved
make reward machine differentiableSHAC · Cheetah RM Task 1return (K): 8.3 -> 15.4 at 3000K stepsImproved
make reward machine differentiableSHAC · Cheetah RM Task 2return (K): 9.1 -> 21.1 at 3000K stepsImproved
use differentiable instead of discrete LTL rewards for PPO/SAC (ablation)PPO/SAC · all environmentsLTL returnNo 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