world-models

There are 3 repositories under world-models topic.

eloialonso / diamond
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.
artificial-intelligence atari deep-learning diffusion-models machine-learning reinforcement-learning research world-models
Language:Python 1642
danijar / dreamerv3
Mastering Diverse Domains through World Models
artificial-intelligence general jax minecraft reinforcement-learning world-models
Language:Python 1428
danijar / dreamerv2
Mastering Atari with Discrete World Models
reinforcement-learning world-models artificial-intelligence robotics deep-learning video-prediction atari research machine-learning
Language:Python 905
eloialonso / iris
Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
artificial-intelligence atari deep-learning machine-learning reinforcement-learning research transformers world-models
Language:Python 812
OpenDriveLab / DriveAGI
[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving & Foundation Models in Autonomous System
autonomous-driving embodied-ai foundation-model general-artificial-intelligence large-dataset policy-learning video-dataset video-generation world-models
Language:Python 638
dreamer
danijar / dreamer
Dream to Control: Learning Behaviors by Latent Imagination
reinforcement-learning artificial-intelligence deep-learning robotics world-models
Language:Python 519
danijar / daydreamer
DayDreamer: World Models for Physical Robot Learning
reinforcement-learning robotics world-models
Language:Jupyter Notebook 283
zhanghm1995 / Forge_VFM4AD
A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.
autonomous-driving survey world-models foundation-model nerf pre-training end-to-end-autonomous-driving large-language-models adaptation 3dgs diffusion
245
johan-gras / MuZero
A structured implementation of MuZero
muzero reinforcement-learning tensorflow world-models
Language:Python 205
HaoranZhuExplorer / World-Models-Autonomous-Driving-Latest-Survey
A curated list of world models for autonomous driving. Keep updated.
autonomous-driving deep-learning self-supervised-learning world-models
197
ucd-dare / CarDreamer
World Model based Autonomous Driving Platform in CARLA :car:
autonomous-driving carla foundation-models model-based-rl reinforcement-learning world-models gym dreamer dreamerv2 dreamerv3
Language:Python 164
Book-of-MLM
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
aigc embodied-ai large-language-models multimodal world-models
Language:HTML 152
lucidrains / genie2-pytorch
Implementation of a framework for Genie2 in Pytorch
artificial-intelligence attention deep-learning transformers world-models
Language:Python 122
danijar / director
Deep Hierarchical Planning from Pixels
algorithms decision-making deep-learning hierarchical-reinforcement-learning planning reinforcement-learning sparse-rewards world-models
Language:Python 91
vmicheli / delta-iris
Efficient World Models with Context-Aware Tokenization. ICML 2024
autoencoders deep-learning machine-learning reinforcement-learning research transformers world-models artificial-inteligence
Language:Python 85
schmidtdominik / LAPO
Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)
imitation-learning policies reinforcement-learning world-models
Language:Python 79
dylandjian / retro-contest-sonic
World Models applied to the Open AI Sonic Retro Contest
world-models reinforcement-learning deep-learning sonic python3 pytorch
Language:Python 77
peg
penn-pal-lab / peg
Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.
exploration reinforcement-learning world-models goal-conditioned-rl model-based-rl
Language:Python 77
jrobine / twm
Transformer-based World Models
artificial-intelligence atari deep-learning iclr2023 machine-learning reinforcement-learning research world-models
Language:Python 74
mazpie / genrl
[NeurIPS 2024] GenRL: Multimodal-foundation world models enable 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.
embodied-agent embodied-ai foundation-models multimodal reinforcement-learning world-models
Language:Python 63
yshen47 / SGAM_NeurIPS22
[NeurIPS 2022] SGAM: Building a Virtual 3D World through Simultaneous Generation and Mapping
3d-generation computer-vision generative-model neurips-2022 world-models
Language:Python 60
chandar-lab / Recall2Imagine
Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024
dreamer iclr2024 model-based-reinforcement-learning model-based-rl reinforcement-learning state-space-models deep-reinforcement-learning deep-rl s4 ssm world-models mamba parallel-scan parallel-scanning s5 s6
Language:Python 57
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
argoverse autonomous-driving imitation-learning pytorch traffic-simulation waymo-challenge waymo-open-dataset world-models
Language:Python 57
ShaneFlandermeyer / tdmpc2-jax
Jax/Flax Implementation of TD-MPC2
reinforcement-learning world-models
Language:Python 49
lucidrains / dreamerv3-pytorch
Implementation of DreamerV3 in Pytorch
artificial-intelligence deep-learning model-based-learning world-models
Language:Python 40
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.
reinforcement-learning skill-learning world-models
Language:Python 38
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.
exploration reinforcement-learning world-models planning skill-learning
Language:Python 34
Deepest-Project / WorldModels-A3C
World Models with A3C on Carracing-v0 in gym
world-models pytorch world-models-rl world-models-a3c a3c actor-critic a3c-lstm model-based-rl car-racing gym vae lstm
Language:Python 32
juliuskunze / cwvae-jax
Clockwork VAEs in JAX/Flax
machine-learning research deep-learning video-prediction world-models jax
Language:Python 32
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
reinforcement-learning sonic-the-hedgehog world-models pytorch curiosity sonic openai-retro-content
Language:Jupyter Notebook 31
thuml / HarmonyDream
Code release for "HarmonyDream: Task Harmonization Inside World Models" (ICML 2024), https://arxiv.org/abs/2310.00344
model-based-reinforcement-learning world-models
Language:Python 27
arnavkj1995 / VSG
Learning Robust Dynamics Through Variational Sparse Gating
deep-reinforcement-learning model-based-reinforcement-learning world-models deep-learning machine-learning research video-prediction
Language:Python 20
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.
language nlp world-models
Language:Python 19
esteveste / dreamerV2-pytorch
Pytorch implementation of DreamerV2: Mastering Atari with Discrete World Models, based on the original implementation
pytorch dreamerv2 fp16 world-models atari
Language:Python 18
dweam-team / awesome-world-model-games
List of world model games and where to find them!
ai-games awesome awesome-list diffusion-models games transformer-models video-models world-models neural-engine video-games ai-minecraft
17
yardenas / jax-dreamer
Dreamer on JAX
reinforcement-learning jax model-based-reinforcement-learning machine-learning world-models
Language:Python 15

world-models

eloialonso / diamond

danijar / dreamerv3

danijar / dreamerv2

eloialonso / iris

OpenDriveLab / DriveAGI

danijar / dreamer

danijar / daydreamer

zhanghm1995 / Forge_VFM4AD

johan-gras / MuZero

HaoranZhuExplorer / World-Models-Autonomous-Driving-Latest-Survey

ucd-dare / CarDreamer

HCPLab-SYSU / Book-of-MLM

lucidrains / genie2-pytorch

danijar / director

vmicheli / delta-iris

schmidtdominik / LAPO

dylandjian / retro-contest-sonic

penn-pal-lab / peg

jrobine / twm

mazpie / genrl

yshen47 / SGAM_NeurIPS22

chandar-lab / Recall2Imagine

zhejz / TrafficBots

ShaneFlandermeyer / tdmpc2-jax

lucidrains / dreamerv3-pytorch

mazpie / choreographer

mazpie / mastering-urlb

Deepest-Project / WorldModels-A3C

juliuskunze / cwvae-jax

wassname / world-models-sonic-pytorch

thuml / HarmonyDream

arnavkj1995 / VSG

princeton-nlp / lwm

esteveste / dreamerV2-pytorch

dweam-team / awesome-world-model-games

yardenas / jax-dreamer