AI Paper Atlas

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

Play to Grade: Testing Coding Games as Classifying Markov Decision Process

Allen Nie, Emma Brunskill, Christopher J Piech

NeurIPS 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Boundedly rational agent modeling · 4 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 transition/reward prediction with HoareLSTM instead of Noisy Supervised LearningCar-Easy bug-state classification · Car-Easy, single-direction agentaccuracy: 91.0 ± 4.7 -> 99.3 ± 1.9Improved
Use transition/reward prediction with HoareLSTM instead of Noisy Supervised LearningCar-Easy bug-state classification · Car-Easy, random agentaccuracy: 60.3 ± 11.8 -> 98.5 ± 1.1Improved
Use Contrastive HoareLSTM instead of code-as-text classificationBounce student programs · Bounce body, balancedaccuracy: 74.2 -> 93.4Improved
Use Contrastive HoareLSTM instead of code-as-text classificationBounce student programs · Bounce tail, balancedaccuracy: 68.4 -> 94.0Improved
Add collaborative training, iteration 1, to HoareLSTM (ablation)Car-Hard bug-state classification · Car-Hardrecall: 80.0 -> 100.0Improved
Add collaborative training, iteration 1, to Contrastive HoareLSTM (ablation)Car-Hard bug-state classification · Car-Hardrecall: 87.1 -> 94.9Improved
Continue collaborative training from iteration 1 to iteration 2 with HoareLSTM (ablation)Car-Hard bug-state classification · Car-Hardaccuracy: 100.0 -> 99.3Mixed
Continue collaborative training from iteration 1 to iteration 2 with Contrastive HoareLSTM (ablation)Car-Hard bug-state classification · Car-Hardaccuracy: 97.2 -> 97.9Improved
Increase provided bug examples from 3 to 10 (ablation)Contrastive HoareLSTM · Bounce body, balancedaccuracy: 50.0 -> 93.4Improved
Increase provided bug examples from 3 to 10 (ablation)Contrastive HoareLSTM · Bounce tail, balancedaccuracy: 50.0 -> 94.0Improved

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