Research map / Multi-agent systems and games / Human-AI and goal-conditioned
People Do Not Just Plan,They Plan to Plan
Mark Ho, David Abel, Jonathan Cohen, Michael Littman, Thomas Griffiths
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Partial Planning Cost predictor to model with seven planning metrics (ablation) | RT mixed-effects model · Experiment 1 | LL ratio chi2(1): 37.71 | Improved |
| add A* Node Count predictor (ablation) | RT mixed-effects model · Experiment 1 | LL ratio chi2(1): 18.60 | Improved |
| add VI Iterations predictor (ablation) | RT mixed-effects model · Experiment 1 | LL ratio chi2(1): 24.12 | Improved |
| add Information Theoretic Bounded Rationality predictor (ablation) | RT mixed-effects model · Experiment 1 | LL ratio chi2(1): 0.82 | No clear effect |
| add RL Softmax Entropy predictor (ablation) | RT mixed-effects model · Experiment 1 | LL ratio chi2(1): 1.50 | No clear effect |
| add Soft-Bellman Entropy predictor (ablation) | RT mixed-effects model · Experiment 1 | LL ratio chi2(1): 10.38 | Improved |
| add Optimal Plan Length predictor (ablation) | RT mixed-effects model · Experiment 1 | LL ratio chi2(1): 14.06 | Improved |
| add Trajectory Turns predictor (ablation) | RT mixed-effects model · Experiment 1 | LL ratio chi2(1): 13.93 | Improved |
| regress item mean log RTs on A* node count instead of partial planning cost | item-level regression · Experiment 1 | R2: 0.12 -> 0.003 | Hurt |
| add Partial-Plan Divergence predictor (ablation) | RT mixed-effects model · Experiment 2 | LL ratio chi2(1): 24.70 | Improved |
| add A* Destination Nodes predictor (ablation) | RT mixed-effects model · Experiment 2 | LL ratio chi2(1): 0.25 | No clear effect |
| add A* Node Difference predictor (ablation) | RT mixed-effects model · Experiment 2 | LL ratio chi2(1): 2.80 | No clear effect |
Closest papers by meaning
- Structurally Guided Task Decomposition in Spatial Navigation Tasks (Student Abstract) (AAAI 2024 · similarity 0.85)
- Chain of Thoughtlessness? An Analysis of CoT in Planning (NeurIPS 2024 · similarity 0.84)
- Learning Hierarchical Task Knowledge for Planning (AAAI 2025 · similarity 0.83)
- LLMs Can Plan Only If We Tell Them (ICLR 2025 · similarity 0.83)
- Look-Ahead Reasoning on Learning Platforms (NeurIPS 2025 · similarity 0.83)
- On the self-verification limitations of large language models on reasoning and planning tasks (ICLR 2025 · similarity 0.83)
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.
