AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Learning Models of Sequential Decision-Making with Partial Specification of Agent Behavior

Vaibhav V. Unhelkar, Julie A. Shah

AAAI 2019 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Boundedly rational agent modeling · 17 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 local change-point input (ablation)VI · Line WorldwKL(Tx): 2.01 -> 1.38Improved
add global Tx constraints via CVI (ablation)VI · Line WorldwKL(Tx): 2.01 -> 0.98Improved
add both auxiliary inputs (ablation)VI · Line WorldHamming dist. (test): 0.53 -> 0.14Improved
add both auxiliary inputs (ablation)VI · HighwaywKL(Tx): 2.11 -> 0.64Improved
add both auxiliary inputs (ablation)VI · HighwaywKL(bx): 1.67 -> 1.58No clear effect
add local change-point input (ablation)VI · HighwayHamming dist. (train): 0.56 -> 0.36Improved
add global Tx constraints via CVI (ablation)VI · HighwayHamming dist. (train): 0.56 -> 0.48Improved
add local input (ablation)VI · Line WorldwKL(bx): 0.85 -> 0.87No clear effect
add global input (ablation)VI-L · HighwaywKL(bx): 1.75 -> 1.50Mixed
model unknown states with AMM (VI) instead of MaxEnt IRLpolicy alignment · Line WorldwKL(pi): 1.08 -> 0.77Improved

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