atlas

Research map / Reinforcement learning / MDPs and planning

Real-Time Reinforcement Learning

NeurIPS 2019 · Reinforcement learning › MDPs and planning · approach: Robust MDP policy gradient · 14 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 RTAC's state-value critic in place of SAC's action-value critic in the real-time settingRTAC versus SAC · MuJoCo real-timereturnHelped
Apply SAC in the real-time RTMDP rather than the turn-based environmentSAC · MuJoCoreturnHurt
Use RTAC rather than SACContinuous-control benchmarks · Ant and HumanoidreturnHelped
Use RTAC under real-time constraints rather than SAC without real-time constraintsAutonomous driving tasks · Avenue: RaceSolo and CityPedestriansreturnHelped
Merge the actor and critic networks (ablation)RTAC · MuJoCo real-timereturnHelped
Add output normalization (ablation)SAC · MuJoCoreturnHelped
Add output normalization (ablation)RTAC with merged actor and critic networks · MuJoCoreturnHelped

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