Search Results - RepositoryStats

92

1.5k

mit

19

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

atari research world-models deep-learning diffusion-models machine-learning reinforcement-learning artificial-intelligence

Created 2024-05-19

25 commits to main branch, last one 2 days ago

dreamerv3 danijar

229

1.4k

mit

28

Mastering Diverse Domains through World Models

jax general minecraft world-models reinforcement-learning artificial-intelligence

Created 2023-01-14

22 commits to main branch, last one 3 months ago

dreamerv2 danijar

195

898

mit

26

Mastering Atari with Discrete World Models

atari research robotics world-models deep-learning machine-learning video-prediction reinforcement-learning artificial-intelligence

Created 2020-12-04

28 commits to main branch, last one 2 years ago

iris eloialonso

80

801

gpl-3.0

24

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

atari research transformers world-models deep-learning machine-learning reinforcement-learning artificial-intelligence

Created 2022-08-23

12 commits to main branch, last one 23 days ago

DriveAGI OpenDriveLab

22

591

apache-2.0

29

[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving & Foundation Models in Autonomous System

embodied-ai world-models large-dataset video-dataset policy-learning foundation-model video-generation autonomous-driving general-artificial-intelligence

Created 2023-04-24

121 commits to main branch, last one 28 days ago

dreamer danijar

110

513

mit

10

Dream to Control: Learning Behaviors by Latent Imagination

robotics world-models deep-learning reinforcement-learning artificial-intelligence

Created 2020-01-27

6 commits to master branch, last one 3 years ago

daydreamer danijar

30

275

unknown

11

DayDreamer: World Models for Physical Robot Learning

robotics world-models reinforcement-learning

Created 2022-09-13

1 commits to main branch, last one about a year ago

Forge_VFM4AD zhanghm1995

10

237

unknown

9

A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.

3dgs nerf survey diffusion adaptation pre-training world-models foundation-model autonomous-driving large-language-models end-to-end-autonomous-driving

Created 2023-11-25

35 commits to master branch, last one 4 months ago

MuZero johan-gras

54

206

unknown

10

A structured implementation of MuZero

muzero tensorflow world-models reinforcement-learning

Created 2019-12-08

13 commits to master branch, last one 4 years ago

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

8

171

unknown

10

A curated list of world models for autonomous driving. Keep updated.

world-models deep-learning autonomous-driving self-supervised-learning

Created 2023-12-18

117 commits to main branch, last one a day ago

CarDreamer ucd-dare

25

149

other

6

World Model based Autonomous Driving Platform in CARLA :car:

gym carla dreamer dreamerv2 dreamerv3 world-models model-based-rl foundation-models autonomous-driving reinforcement-learning

Created 2024-05-12

189 commits to master branch, last one 13 days ago

Book-of-MLM HCPLab-SYSU

12

127

unknown

2

《多模态大模型：新一代人工智能技术范式》作者：刘阳，林倞

aigc multimodal embodied-ai world-models large-language-models

Created 2024-02-22

110 commits to main branch, last one 5 months ago

director danijar

22

90

unknown

4

Deep Hierarchical Planning from Pixels

planning algorithms world-models deep-learning sparse-rewards decision-making reinforcement-learning hierarchical-reinforcement-learning

Created 2022-08-22

1 commits to main branch, last one about a year ago

delta-iris vmicheli

9

84

gpl-3.0

3

Efficient World Models with Context-Aware Tokenization. ICML 2024

research autoencoders transformers world-models deep-learning machine-learning artificial-inteligence reinforcement-learning

Created 2024-05-29

7 commits to main branch, last one about a month ago

LAPO schmidtdominik

7

73

unknown

2

Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)

policies world-models imitation-learning reinforcement-learning

Created 2024-03-18

8 commits to main branch, last one 3 months ago

peg penn-pal-lab

4

72

mit

3

Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.

exploration world-models model-based-rl goal-conditioned-rl reinforcement-learning

Created 2023-03-10

7 commits to master branch, last one about a year ago

twm jrobine

8

71

mit

5

Transformer-based World Models

atari iclr2023 research world-models deep-learning machine-learning reinforcement-learning artificial-intelligence

Created 2022-09-28

5 commits to main branch, last one about a year ago

SGAM_NeurIPS22 yshen47

4

59

unknown

3

[NeurIPS 2022] SGAM: Building a Virtual 3D World through Simultaneous Generation and Mapping

neurips-2022 world-models 3d-generation computer-vision generative-model

Created 2022-10-23

54 commits to main branch, last one 9 months ago

genrl mazpie

0

57

mit

2

[NeurIPS 2024] 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 seq...

multimodal embodied-ai world-models embodied-agent foundation-models reinforcement-learning

Created 2024-06-25

2 commits to main branch, last one 3 months ago

TrafficBots zhejz

8

55

other

4

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

pytorch argoverse world-models waymo-challenge autonomous-driving imitation-learning traffic-simulation waymo-open-dataset

Created 2023-09-22

2 commits to main branch, last one about a year ago

Recall2Imagine chandar-lab

5

50

mit

7

Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024

s4 s5 s6 ssm mamba deep-rl dreamer iclr2024 world-models parallel-scan model-based-rl parallel-scanning state-space-models reinforcement-learning deep-reinforcement-learning model-based-reinforcement-learning

Created 2024-03-25

2 commits to main branch, last one 5 months ago

tdmpc2-jax ShaneFlandermeyer

6

46

unknown

4

Jax/Flax Implementation of TD-MPC2

world-models reinforcement-learning

Created 2024-03-11

18 commits to main branch, last one 14 days ago

choreographer mazpie

5

35

mit

1

[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 tas...

world-models skill-learning reinforcement-learning

Created 2023-02-22

2 commits to main branch, last one 4 months ago

mastering-urlb mazpie

6

33

mit

2

[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.

planning exploration world-models skill-learning reinforcement-learning

Created 2023-07-11

6 commits to main branch, last one 8 months ago

HarmonyDream thuml

1

26

mit

6

Code release for "HarmonyDream: Task Harmonization Inside World Models" (ICML 2024), https://arxiv.org/abs/2310.00344

world-models model-based-reinforcement-learning

Created 2024-06-04

5 commits to main branch, last one 4 months ago