/Awesome-world-model

This is a collection of research papers for world model

Awesome-world-model

This is a collection of research papers for world model

- Wolrd Model
|- Generalization
|- Dynamic Modeling
|- Representation Learning
- Utilities

World Models Meet Languages

Tutorials and Surveys

  • Language Models Meet World Models, Zhiting Hu, Tianmin Shu, Neurips 2023, slides, pdf
  • A Survey of Reinforcement Learning Informed by Natural Language, Jelena Luketina1, Nantas Nardelli, Gregory Farquhar, Tim Rocktäschel et al.

External Soul Bones

  • Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning, Lin Guan, Karthik Valmeekam, Sarath Sreedharan, Subbarao Kambhampati, Neurips 2023
  • Language Models Meet World Models: Embodied Experiences Enhance Language Models, Jiannan Xiang, Tianhua Tao, et al., Neurips 2023

Generalization

Dreamer branch

  • Iso-Dream: Isolating Noncontrollable Visual Dynamics in World Models, Minting Pan, Xiangming Zhu, Yunbo Wang, Xiaokang Yang, Neurips 2022, link
    • dreamer, disentangle, background generalization.
  • DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations, Fei Deng, Ingook Jang, Sungjin Ahn, ICML 2022, link
    • dreamer, SwAV, representation enhancement.

Dynamic Modeling

Dreamer branch

  • Transformers are Sample-Efficient World Models, Vincent Micheli, Eloi Alonso, François Fleuret, preprint 2022, link

    • dreamer, discrete, atari

  • TransDreamer: Reinforcement Learning with Transformer World Models, Chang Chen, Yi-Fu Wu, Jaesik Yoon, Sungjin Ahn, preprint 2022, link

  • Dreaming with Transformers. Catherine Zeng, Jordan Docter, Alexander Amini, Igor Gilitschenski, Ramin Hasani, Daniela Rus, AAAI 2022, Workshop on Reinforcement Learning in Games, link

Representation Learning

Dreamer branch

  • Masked World Models for Visual Control. Younggyo Seo, Danijar Hafner, Hao Liu, Fangcheng Liu, Stephen James, Kimin Lee, Pieter Abbeel. CoRL 2022. link
    • dreamer, mae, representation learning.

Transferability

  • Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting. Under Reveiw. ICLR 2023. link

Language in World Model

Utilities

  • Unsupervised Learning of Visual Featuresby Contrasting Cluster Assignments, Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, Armand Joulin, Neurips 2020 link
    • SwAV, unsupervised pre-training, contrastive, prototypes.