Mastering Diverse Domains through World Models
-
Updated
May 16, 2024 - Python
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
Related papers for reinforcement learning, including classic papers and latest papers in top conferences
DayDreamer: World Models for Physical Robot Learning
A structured implementation of MuZero
A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.
Deep Hierarchical Planning from Pixels
A curated list of world models for autonomous driving. Keep updated.
World Models applied to the Open AI Sonic Retro Contest
Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.
[NeurIPS 2022] SGAM: Building a Virtual 3D World through Simultaneous Generation and Mapping
Transformer-based World Models
TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction. ICRA 2023.
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model.
Recall 2 Imagine, a World Model with superhuman memory. Oral (1.2%) @ ICLR 2024
Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)
《多模态大模型:新一代人工智能技术范式》作者:刘阳,林倞
World Models with A3C on Carracing-v0 in gym
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."