AI Paper Atlas

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

A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning

Harry Zhao, Zhen Liu, Sitao Luan, Shuyuan Zhang, Doina Precup, Yoshua Bengio

NeurIPS 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Language-grounded reinforcement agents · 10 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 consciousness-inspired bottleneck (CP(8)) to set-based MPC planner (ablation)UP (set-based MBRL agent) · OOD MiniGrid lava navigation 8x8success rateImproved
use MPC planning instead of Dyna with true modelDyna* baseline · OOD MiniGrid lava navigation 8x8success rateNo clear effect
two-stage world-model pretraining instead of end-to-end training (ablation)CP · in-distribution MiniGridsuccess rateHurt
add action regularization (inverse-model loss) in bottleneck (ablation)CP(4) · OOD MiniGrid difficulty 0.35success rateImproved
semi-hard top-k attention instead of soft attention for selection (ablation)CP · in-distribution dynamics accuracyrelative L1 errorMixed
vectorized representation instead of set representation (NOSET)UP · in-distribution MiniGridsuccess rateHurt
add noise input to dynamics model (CP(8)+) (ablation)CP(8) · color-distraction Turn-and-Forward OODsuccess rateNo 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