[ICLR 2025 Oral] PyTorch code for the paper "Open-World Reinforcement Learning over Long Short-Term Imagination"

Modular DRL framework for autonomous robot navigation in ROS2. Plug-and-play RL backends (Stable-Baselines3, DreamerV3), composable reward functions, observation spaces & neural architectures - built for research and deployment.

Flax Implementation of DreamerV3 on Crafter

PyTorch implementation of DreamerV3 from "Mastering Diverse Domains with World Models"

Hierarchical learning by dreaming for empowering control with latent skills in imagination

[ICLR 2025 Oral] PyTorch code for the paper "Open-World Reinforcement Learning over Long Short-Term Imagination"

The implementation of pytorch-based DreamerV3 for Meta-world simulator.

DreamerV3 World Model RL from Scratch — Educational implementation of model-based reinforcement learning

One unified API for world models that imagine, plan, and act — a PyTorch toolkit shipping DreamerV3, TD-MPC2, and more

A template for deploying DreamerV3 with Ray RLlib, compatible with Gym and custom environments.

🌍 Investigating the understanding of spatio-temporal information in World Models | Research Project in World Models 2024 by The University of Tokyo

Learning to fly FPV but in dreams!

Reinforcement Learning : Autonomous parallel parking task. implementing SAC and DreamerV3's World Model on Highway-env

Implement Dreamerv3 to train robots in webots

Fishy RL is a distributed reinforcement learning framework for model-based and model-free algorithms. It is designed to be flexible and user-friendly, allowing researchers and practitioners to easily interchange components and environments

Hierarchical extension of Dreamer-V3 pytorch implementation. Decouples low level and high level features in the latent space.