The authors introduce Generative Trajectory Planning (GTP), a model-based framework that treats decision making as generative inference.
Generative models as proposal distributions improve long-horizon decision making
The GTP framework samples action sequences from a diffusion prior and refines them with learned dynamics and value models, outperforming RL and diffusion-policy baselines on continuous control and manipulation tasks.
Top University
Haldun Balim · Yilun Du · Na Li
Harvard University
Research Digest··2 min read
The authors propose Generative Trajectory Planning (GTP), a model-based framework for online decision making that uses a learned generative model as a proposal distribution over action sequences.
Why this paper
From Harvard University
In one line
Generative Trajectory Planning uses a generative model as a proposal distribution for action sequences enabling efficient long-horizon planning.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§