AI Paper Atlas

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

A Direct Approximation of AIXI Using Logical State Abstractions

Samuel Yang-Zhao, Tianyu Wang, Kee Siong Ng

NeurIPS 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Language-grounded reinforcement agents · 1 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 Phi-AIXI-CTW instead of U-Tree and PARSS-DTRL agent · Biased RPS, Taxi, Jackpot, Stop Heistlearning curve rewardImproved
Use Phi-AIXI-CTW instead of U-Tree and PARSSRL agent · Jackpot and Taxilearning curve rewardImproved
Use Phi-AIXI-CTW instead of U-TreeRL agent · Biased RPS and Stop Heistlearning curve rewardNo clear effect
Use Phi-AIXI-CTW instead of U-Tree and PARSSRL agent · Epidemic control, lambda=1learning curve rewardImproved
Use RF-BDD instead of Random Forest feature selection (ablation)Phi-AIXI-CTW · Epidemic controllearning curve rewardMixed
Increase vaccination efficacy (eta 2,4 -> 10,20)Phi-AIXI-CTW with RF-BDD · Epidemic control, lambda=10average reward per cycleImproved
Lower infection weighting lambda from 10 to 1Phi-AIXI-CTW · Epidemic controlagent activityMixed
Forward selection instead of Random Forest feature selection (ablation)Phi-AIXI-CTW · Epidemic controlperformanceNo clear effect

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