Mastering Atari with Discrete World Models
-
Updated
Jan 21, 2023 - Python
Mastering Atari with Discrete World Models
Mastering Diverse Domains through World Models
Dream to Control: Learning Behaviors by Latent Imagination
Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
A structured implementation of MuZero
DayDreamer: World Models for Physical Robot Learning
Deep Hierarchical Planning from Pixels
Related papers for reinforcement learning, including classic papers and latest papers in top conferences
World Models with A3C on Carracing-v0 in gym
World Model based Autonomous Driving Platform in CARLA 🚗
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model.
World Models applied to the Open AI Sonic Retro Contest
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
A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.
[ICML 2023] Pre-train world model-based agents with different unsupervised strategies, fine-tune the agent's components selectively, and use planning (Dyna-MPC) during fine-tuning.
Pytorch implementation of DreamerV2: Mastering Atari with Discrete World Models, based on the original implementation
A curated list of world models for autonomous driving. Keep updated.
《多模态大模型:新一代人工智能技术范式》作者:刘阳,林倞
[ICLR 2023] Choreographer: a model-based agent that discovers and learns unsupervised skills in latent imagination, and it's able to efficiently coordinate and adapt the skills to solve downstream tasks.
Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024
Add a description, image, and links to the world-models topic page so that developers can more easily learn about it.
To associate your repository with the world-models topic, visit your repo's landing page and select "manage topics."