AI Paper Atlas

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

Uncertainty-Aware Reinforcement Learning for Risk-Sensitive Player Evaluation in Sports Game

Guiliang Liu, Yudong Luo, Oliver Schulte, Pascal Poupart

NeurIPS 2022 · Reinforcement learning › Policy gradient and actor-critic · approach: Temporal-difference and discounting theory · 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
Add risk-aware distributional estimates (RiGIM at c=0.5) over risk-neutral GIMGIM · NHL Assist correlationcorrelation: 0.456 -> 0.675Improved
Add risk-aware distributional estimates (RiGIM at c=0.5) over risk-neutral GIMGIM · Soccer Assist correlationcorrelation: 0.462 -> 0.577Improved
Remove the epistemic uncertainty estimator (Na-RiGIM) (ablation)RiGIM · NHL Point correlationcorrelation: 0.678 -> 0.625Hurt
Remove the epistemic uncertainty estimator (Na-RiGIM) (ablation)RiGIM · Soccer Key Passes correlationcorrelation: 0.574 -> 0.503Hurt
Replace SP-CNF with GDA density estimator (ablation)RiGIM · NHL TOI correlationcorrelation: 0.68 -> 0.593Hurt
Replace SP-CNF with GDA density estimator (ablation)RiGIM · Soccer Drb/KeyP correlationcorrelation: 0.574 -> 0.478Hurt
Filter OoD events by low density in RiGIM (ablation)RiGIM · NHL SHG correlationcorrelation: 0.134 -> 0.11Hurt
Tune confidence level c on validation set (c*=0.34) instead of 0.5RiGIM · NHL Assist correlationcorrelation: 0.675 -> 0.68No clear effect
Tune confidence level c on validation set (c*=0.49) instead of 0.5RiGIM · Soccer Goal correlationcorrelation: 0.671 -> 0.682No clear effect
Make RiGIM more risk-seeking by lowering cRiGIM · NHL success measurescorrelationMixed
Replace tabular Scoring Impact with neural recurrent value modelsSI · NHL Goal correlationcorrelation: 0.596 -> 0.477Mixed
Use distribution estimates (RiGIM) versus expected values with FS-CNF filteringRiGIM · Scoring chance match, binsabsolute differenceImproved

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