Model-Based RL in the Era of Generative World Models
Reinforcement Learning Conference (RLC) Workshop
August 15, 2026, Montreal, Canada
Submit Your Paper

Outstanding contributions receive a Best Paper Award

Core Topics

Where model-based RL meets the new wave of large-scale generative world models.

  • Model-Based RL Algorithms & Theory
  • Planning & Search in Learned Models
  • Exploration & Sample Efficiency
  • Generative & Latent World Models
  • World Models for Sim-to-Real Transfer
  • Offline RL & Model-Based Imagination

Invited Speakers actively updating

Danijar Hafner

Danijar Hafner

Google DeepMind

Tentative
Doina Precup

Doina Precup

Google DeepMind & McGill University

Confirmed
Harry Zhao

Harry Zhao

Wayve

Confirmed
Cyrus Neary

Cyrus Neary

University of British Columbia

Confirmed
Amir Zadeh

Amir Zadeh

Lambda AI

Confirmed
Scott Fujimoto

Scott Fujimoto

AMI Labs

Confirmed

Schedule Tentative

The program below is tentative and subject to change.

Time Event Speaker
9:00 – 9:15 Opening Remarks
9:15 – 10:00 Invited Talk 1 Harry Zhao
10:00 – 10:45 Invited Talk 2 Scott Fujimoto
10:45 – 11:15 Coffee Break & Networking
11:15 – 12:00 Invited Talk 3 Danijar Hafner
12:00 – 13:00 Lunch Break
13:00 – 13:45 Invited Talk 4 Amir Zadeh
13:45 – 14:30 Invited Talk 5 Doina Precup
14:30 – 15:30 Poster Session
15:30 – 16:15 Invited Talk 6 Cyrus Neary
16:15 – 16:30 Closing Remarks

Accepted Papers

15 papers accepted to MBRL+WM 2026. Congratulations to all authors! Full papers are available on OpenReview.

Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models

Shukrullo Nazirjonov, Sai Prasanna, Anna Manasyan, Georg Martius

Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty

Artur Eisele, Bernd Frauenknecht, Friedrich Solowjow, Sebastian Trimpe

Hierarchical Reinforcement Learning with Temporally-extended Latent Action World Models

Dan Haramati, Chandradithya S Jonnalagadda, Akhil Bagaria, George Konidaris

Best Paper

One Flow-Transformer for Imagination and Control

Rabiul Awal, Jinseong Jeong, Ankur Sikarwar, Parisa Kordjamshidi, Andrii Zadaianchuk, Sai Rajeswar, Paul Hongsuck Seo, Aishwarya Agrawal

Optimistic World Models: Model-Space Exploration for Deep MBRL

Akshay Mete, Shahid Aamir Sheikh, Tzu-Hsiang Lin, Dileep Kalathil, Panganamala Kumar

Principled Latent Actions through Policy Discrimination

Max Rudolph, Caleb Chuck, Fan Feng, Amy Zhang

Valdi: Value Diffusion World Models

Christopher Lindenberg, Kashyap Chitta

World Models for POMDPs: Deep Belief Markov Models for Partially Observable Model-Based Reinforcement Learning

Giacomo Arcieri, Kostas G. Papakonstantinou, Daniel Straub, Eleni Chatzi

World-Model Reinforcement Learning for Reward Machines with Unknown Labels

Pranav Tiwari, Dominik Wagner, Debraj Chakraborty, Luke Ong

Sponsors

We are grateful for the support from our partners in advancing world modeling research.

Organizers

Mohamad H. Danesh

Mohamad H. Danesh

McGill University & Mila
Organizer

Amin Abyaneh

Amin Abyaneh

McGill University & Mila
Organizer

Michael Przystupa

Michael Przystupa

Vrije Universiteit Amsterdam
Organizer

Chenhao Li

Chenhao Li

ETH Zurich
Organizer

Huihan Liu

Huihan Liu

UT Austin
Organizer

Glen Berseth

Glen Berseth

UdeM & Mila
Senior Advisor

Stan Birchfield

Stan Birchfield

Nvidia
Senior Advisor

Hsiu-Chin Lin

Hsiu-Chin Lin

McGill University & Mila
Senior Advisor

Call for Papers

Submission Deadline

May 30, 2026

Anywhere on Earth (AOE)

Author Notification

June 15, 2026

June 25, 2026

Anywhere on Earth (AOE)

Workshop Date

August 15, 2026

Montreal, Canada

Format

Non-archival

Review

Double-blind via OpenReview

Length

4 pp. max + refs./app.

Template

RLC 2026

Submit Your Paper

Outstanding contributions receive a Best Paper Award

Contact

Questions about the workshop or submissions? worldmodelworkshop@gmail.com