dreamerv3
daydreamer
dreamerv3 | daydreamer | |
---|---|---|
3 | 4 | |
1,045 | 220 | |
- | - | |
3.7 | 10.0 | |
10 days ago | over 1 year ago | |
Python | Jupyter Notebook | |
MIT License | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
dreamerv3
- It would be cool if there was a machine learning Nes Emulator, that the ai could learn to play automatically and you just run it on your pc till it finds the optimum root.
- Mastering Diverse Domains through World Models - DreamerV3 - Deepmind 2023 - First algorithm to collect diamonds in Minecraft from scratch without human data or curricula! Now with github links!
- [R] [N] Mastering Diverse Domains through World Models - DreamerV3 - Deepmind 2023 - First algorithm to collect diamonds in Minecraft from scratch without human data or curricula! Now with github links!
daydreamer
-
Self-learning of the robot in 1 hour
Just saw that our video was posted here. For people interested in the research, here is the project website with the research paper: https://danijar.com/daydreamer
-
Reinforcement learning or computer vision
This is a complex model but seems to hit most ideas you are interested in https://github.com/danijar/daydreamer. Skim over it, then with the questions you picked up go through the hugging face RL course and then go back to the paper https://huggingface.co/deep-rl-course/unit1/introduction
- Mastering Diverse Domains through World Models - DreamerV3 - Deepmind 2023 - First algorithm to collect diamonds in Minecraft from scratch without human data or curricula! Now with github links!
- [R] [N] Mastering Diverse Domains through World Models - DreamerV3 - Deepmind 2023 - First algorithm to collect diamonds in Minecraft from scratch without human data or curricula! Now with github links!
What are some alternatives?
dreamerv2 - Mastering Atari with Discrete World Models
dreamer - Dream to Control: Learning Behaviors by Latent Imagination
crafter - Benchmarking the Spectrum of Agent Capabilities
CenterSnap - Pytorch code for ICRA'22 paper: "Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation"
iris - Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
pillbox - Contains implementation of AdVIL, AdRIL, and DAeQuIL algorithms from the ICML '21 Paper Of Moments and Matching.
Datapack-Converter - Convert Minecraft command block chains to a datapack!
brax - Massively parallel rigidbody physics simulation on accelerator hardware.
fractal_rl - Code for CORL 2020 paper: Explicitly Encouraging Low Fractional Dimensional Trajectories Via Reinforcement Learning.
language-table - Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.