[ICLR 2025 Oral] PyTorch code for the paper "Open-World Reinforcement Learning over Long Short-Term Imagination"
A Simplified Pytorch Version of the Dreamer Algorithm
Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024
🌀 FlashForge firmware tool allow you to decrypt and encrypt firmwares from FlashForge 3D printers, Dremel 3D20 and PowerSpec Ultra 3D
From-scratch PyTorch reproduction of DreamerV4 (Hafner et al., 2025): masked-autoencoder tokenizer, block-causal flow-matching dynamics with bootstrap curriculum, agent-token finetuning, and PMPO imagination RL. Trains end-to-end on a single GPU
A modular PyTorch library designed for learning, training, and deploying world models across various environments.
Official implementation of the Informed Dreamer algorithm, based on DreamerV3
Simplistic Pytorch Implementation of the Dreamer-RL
C++ Deep Reinforcement Learning Agent library
Build world models from scratch — from perception and latent dynamics to planning, JEPA, VLA, and 3D/4D intelligence.
Curated papers, code, datasets, and benchmarks for medical world models in imaging, EHR trajectories, treatment planning, surgical AI, robotics, and virtual-cell simulation.
Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization
The implementation of pytorch-based DreamerV3 for Meta-world simulator.
[ICLR 2025 Oral] PyTorch code for the paper "Open-World Reinforcement Learning over Long Short-Term Imagination"
From next-token to next-state — a curated, opinionated map of world models, tagged by what each system predicts as the next state. Five-Axes framework, landscape map, and a live site.
🌍 可玩的最小「纯隐式世界模型」demo(无坐标/无撞墙判定,全靠神经网络在 latent 空间想象)+ 世界模型高热度论文精读总结。一起探讨世界模型 微信:wzytg001
Trains a deep reinforcement learning agent in simulation testbed environments with the DRLA library.
To associate your repository with the dreamer topic, visit your repo's landing page and select "manage topics."