world-models
There are 49 repositories under world-models topic.
danijar/dreamerv3
Mastering Diverse Domains through World Models
danijar/dreamerv2
Mastering Atari with Discrete World Models
eloialonso/iris
Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
danijar/dreamer
Dream to Control: Learning Behaviors by Latent Imagination
danijar/daydreamer
DayDreamer: World Models for Physical Robot Learning
zhanghm1995/Forge_VFM4AD
A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.
johan-gras/MuZero
A structured implementation of MuZero
eloialonso/diamond
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model.
HaoranZhuExplorer/World-Models-Autonomous-Driving-Latest-Survey
A curated list of world models for autonomous driving. Keep updated.
ucd-dare/CarDreamer
World Model based Autonomous Driving Platform in CARLA :car:
HCPLab-SYSU/Book-of-MLM
《多模态大模型:新一代人工智能技术范式》作者:刘阳,林倞
danijar/director
Deep Hierarchical Planning from Pixels
dylandjian/retro-contest-sonic
World Models applied to the Open AI Sonic Retro Contest
penn-pal-lab/peg
Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.
vmicheli/delta-iris
Efficient World Models with Context-Aware Tokenization. ICML 2024
jrobine/twm
Transformer-based World Models
schmidtdominik/LAPO
Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)
yshen47/SGAM
[NeurIPS 2022] SGAM: Building a Virtual 3D World through Simultaneous Generation and Mapping
zhejz/TrafficBots
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
chandar-lab/Recall2Imagine
Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024
mazpie/genrl
[GenRL] Multimodal foundation world models allow grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state sequences can be decoded using the decoder of the model, allowing visualization of the expected behavior, before training the agent to execute it.
ShaneFlandermeyer/tdmpc2-jax
Jax/Flax Implementation of TD-MPC2
Deepest-Project/WorldModels-A3C
World Models with A3C on Carracing-v0 in gym
mazpie/choreographer
[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.
juliuskunze/cwvae-jax
Clockwork VAEs in JAX/Flax
mazpie/mastering-urlb
[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.
wassname/world-models-sonic-pytorch
Attempt at reinforcement learning with curiosity for Sonic the Hedgehog games. Number 149 on OpenAI retro contest leaderboard, but more work needed
thuml/HarmonyDream
Code release for "HarmonyDream: Task Harmonization Inside World Models" (ICML 2024), https://arxiv.org/abs/2310.00344
arnavkj1995/VSG
Learning Robust Dynamics Through Variational Sparse Gating
esteveste/dreamerV2-pytorch
Pytorch implementation of DreamerV2: Mastering Atari with Discrete World Models, based on the original implementation
Charmve/gpt-eyes
I GAVE GPT-4 EYES!
yardenas/jax-dreamer
Dreamer on JAX
princeton-nlp/lwm
We develop world models that can be adapted with natural language. Intergrating these models into artificial agents allows humans to effectively control these agents through verbal communication.
arnaudvl/world-models-ppo
PyTorch World Model implementation with PPO.
mazpie/contrastive-aif
[NeurIPS 2021] Contrastive learning formulation of the active inference framework, for matching visual goal states.
wegfawefgawefg/wegs-drl-baselines
Minimum viable reinforcement learning algorithms for your educational convenience.