RESEARCH PAPERYear 2020

Model-Based Reinforcement Learning for Atari

Lukasz Kaiser; Mohammad Babaeizadeh; Piotr Milos; Blazej Osinski; Roy H. Campbell; Konrad Czechowski; Dumitru Erhan; Chelsea Finn; Piotr Kozakowski; Sergey Levine; Afroz Mohiuddin; Ryan Sepassi; George Tucker; Henryk Michalewski

Read paper PDF

Classification

View four quadrants

Major category: Foundational work
Quadrant: Not applicable
Architecture: Not applicable
Prediction paradigm: Not applicable
Subcategories: Classical world models & model-based RL
Source review status: Verified from primary sources

Category review. SimPLe is a pre-2026 foundational learned-video-simulator approach to sample-efficient reinforcement learning. Alternating real collection, model learning and simulated PPO training establishes a historical world-model learning loop. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX

@inproceedings{atari100k,
  author       = {Lukasz Kaiser and
                  Mohammad Babaeizadeh and
                  Piotr Milos and
                  Blazej Osinski and
                  Roy H. Campbell and
                  Konrad Czechowski and
                  Dumitru Erhan and
                  Chelsea Finn and
                  Piotr Kozakowski and
                  Sergey Levine and
                  Afroz Mohiuddin and
                  Ryan Sepassi and
                  George Tucker and
                  Henryk Michalewski},
  title        = {Model Based Reinforcement Learning for Atari},
  booktitle    = {ICLR},
  year         = {2020},

}

Classification

Contribution

Abstract

Affiliations

BibTeX

More in this category

Critique of World Model

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning

Mean Flows for One-step Generative Modeling