AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Conformal Prediction for Uncertainty-Aware Planning with Diffusion Dynamics Model

Jiankai Sun, Yiqi Jiang, Jianing Qiu, Parth Talpur Nobel, Mykel Kochenderfer, Mac Schwager

NeurIPS 2023 · Reinforcement learning › Offline RL · approach: Decision Transformer sequence models · 3 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
add conformal-prediction uncertainty loss (PlanCP) to Diffuser trainingDiffuser · Maze2D U-Mazereward: 113.9 -> 116.4Improved
add conformal-prediction uncertainty loss (PlanCP)Diffuser · Maze2D Mediumreward: 121.5 -> 128.5Improved
add conformal-prediction uncertainty loss (PlanCP)Diffuser · Maze2D Largereward: 123.0 -> 130.9Improved
add conformal-prediction uncertainty loss (PlanCP)Diffuser · Maze2D U-Mazeuncertainty interval width: 25.36 -> 21.74Improved
add conformal-prediction uncertainty loss (PlanCP)Diffuser · Maze2D Mediumuncertainty interval width: 9.08 -> 10.22Hurt
add conformal-prediction uncertainty loss (PlanCP)Diffuser · Maze2D Largeuncertainty interval width: 71.12 -> 70.71No clear effect
add conformal-prediction uncertainty loss (PlanCP)Diffuser · D4RL HalfCheetah medium-expertinterval width: 9.34 -> 8.68Improved
add conformal-prediction uncertainty loss (PlanCP)Diffuser · D4RL Walker2d medium-expertinterval width: 1.10 -> 2.56Hurt
add conformal-prediction uncertainty loss (PlanCP)Diffuser · D4RL HalfCheetah mediumreturn: 46.10 -> 46.26No clear effect
add conformal-prediction uncertainty loss (PlanCP)Diffuser · D4RL Walker2d mediumreturn: 75.73 -> 77.08No clear effect
add conformal-prediction uncertainty loss (PlanCP)Diffuser · D4RL Walker2d medium-replayreturn: 52.24 -> 54.53No clear effect
add conformal-prediction uncertainty loss (PlanCP)Diffuser · D4RL average over six tasksreturn: 67.58 -> 68.55Improved

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