Mastering Diverse Domains through World Models

Mastering Atari with Discrete World Models

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

Dream to Control: Learning Behaviors by Latent Imagination

DayDreamer: World Models for Physical Robot Learning

A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model.

A structured implementation of MuZero

A curated list of world models for autonomous driving. Keep updated.

World Model based Autonomous Driving Platform in CARLA 🚗

《多模态大模型：新一代人工智能技术范式》作者：刘阳，林倞

Deep Hierarchical Planning from Pixels

World Models applied to the Open AI Sonic Retro Contest

Efficient World Models with Context-Aware Tokenization. ICML 2024

Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.

Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)

Transformer-based World Models

[NeurIPS 2022] SGAM: Building a Virtual 3D World through Simultaneous Generation and Mapping

TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction. ICRA 2023. You may also want to check out the updated version: https://github.com/zhejz/TrafficBotsV1.5

[NeurIPS 2024] GenRL: Multimodal foundation world models allow grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state sequences can be decoded using the decoder of the model, allowing visualization of the expected behavior, before training the agent to execute it.