Skip to content
AI News HubLIVE
Original source2 min read

From Self-Play RL to Constrained Control: Distilling DiffMPC Students with DAgger

Summary

This paper proposes replacing the action head of a trained self-play reinforcement learning driving policy with a differentiable model predictive control (DiffMPC) module that enforces road-boundary and agent constraints, then distilling the student with DAgger in the teacher's self-play simulator. Across 9 seeds, the constrained student matches its smaller teacher on nuPlan and beats it on CARLA and out-of-distribution Waymo scenes, with distillation taking no more than 30% of the teacher's training time.

SourcearXiv RoboticsAuthor: Luca M. Hartmann, Parinaz Naghizadeh
From Self-Play RL to Constrained Control: Distilling DiffMPC Students with DAgger
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 18 Nov 2026]

Title:From Self-Play RL to Constrained Control: Distilling DiffMPC Students with DAgger

View a PDF of the paper titled From Self-Play RL to Constrained Control: Distilling DiffMPC Students with DAgger, by Luca M. Hartmann and 1 other authors

View PDF HTML (experimental)

Abstract:Self-play reinforcement learning (RL) produces strong driving policies, but these policies are hard to verify or interpret. Differentiable model predictive control (DiffMPC) can enforce explicit constraints, but it is usually trained by imitating logged data or with costly RL. To add constraints to an already trained policy, we keep a PPO teacher's backbone and replace its action head with a DiffMPC that enforces road boundary half-planes and agent ellipses. We then distill the student with DAgger in the teacher's self-play simulator. Over 9 seeds, the constrained student of a smaller teacher matches its teacher on nuPlan and beats it on CARLA and on out-of-distribution Waymo scenes. For a stronger teacher, the student has fewer failures on nuPlan and Waymo, while staying level on CARLA. Its distillation takes no more than 30% of the teacher's training time.

Comments: 18 pages, 10 main content pages, 3 figures, L4DC submission

Subjects:

Robotics (cs.RO); Machine Learning (cs.LG); Systems and Control (eess.SY)

Cite as: arXiv:2611.25197 [cs.RO]

(or arXiv:2611.25197v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2611.25197

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Luca M. Hartmann [view email] [v1] Wed, 18 Nov 2026 21:17:04 UTC (87 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled From Self-Play RL to Constrained Control: Distilling DiffMPC Students with DAgger, by Luca M. Hartmann and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.RO

new | recent | 2026-11

Change to browse by:

cs cs.LG cs.SY eess eess.SY

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Keeps a PPO teacher's backbone and swaps its action head for a DiffMPC module enforcing road boundary half-planes and agent ellipses.
  • Distills the student with DAgger inside the teacher's self-play simulator across 9 seeds.
  • The smaller teacher's constrained student matches the teacher on nuPlan and outperforms it on CARLA and out-of-distribution Waymo.
  • For a stronger teacher, the student has fewer failures on nuPlan and Waymo while staying level on CARLA, with distillation under 30% of teacher training time.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

From Self-Play RL to Constrained Control: Distilling DiffMPC Students with DAgger | AI News Hub