This is the official implementation of DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations in TensorFlow 2. A re-implementation of Temporal Predictive Coding for Model-Based Planning in Latent Space is also included.
The main features of fdeng18/dreamer-pro are: Embodied World Models.
Open-source alternatives to fdeng18/dreamer-pro include: agibottech/ewmbench — Official code for EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models. aidanscannell/dcmpc — This repository is the official implementation of DC-MPC, presented in "Discrete Codebook World Models for Continuous… alibaba-damo-academy/worldvla — RynnVLA-002: A Unified Vision-Language-Action and World Model. anh-nn01/time-aware-world-model — ⏱️ Time-Aware World Model 🌎 🎓 Paper | 📌 Poster | 🌐 Website | 🎬 Videos. aria-zhangjl/storyweaver — This is an official implementation of AAAI 2025 paper StoryWeaver: A Unified World Model for Knowledge-Enhanced Story… 20robo/raenwm — Paper | Models (Coming Soon).
Official code for EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models
This repository is the official implementation of DC-MPC, presented in "Discrete Codebook World Models for Continuous Control" at ICLR 2025. DC-MPC is a model-based reinforcement learning algorithm demonstrating the strengths of learning a discrete latent space with discrete codebook encodings.
RynnVLA-002: A Unified Vision-Language-Action and World Model
