Comments (2)
First, thanks for using Minari! And these questions are really helpful for us; it's difficult to refine a product without hearing from users.
OK so for the first part. We are working on a optional https://docs.mosaicml.com/projects/streaming/en/stable/ streamingdataset backend. We are open to design suggestions for parallel sampling for both a streaming dataset and h5py backend(I'm not sure what we need to do to get true parallelism in python in the setting of memory shared between physical threads, maybe this is easy). It may be that a parallel sampling implementation could be a strict improvement over our current implementation on any machine with more than once physical CPU core.
For the second one. We don't have any built-in features for sampling from multiple datasets at once. The closest thing that comes to mind is generating the list of indices to sample externally to minari, then sampling from each dataset using iterate_episodes
with that list as an argument (you can also use square brackets directly on the MinariDataset
object to get a episode by index). That will give you fine-grained enough control to sample without replacement, or sample the same indices from different datasets, etc... We have sub-episode trajectory sampling code in development also.
We are open to feature requests, so feel free to propose any features you think would support your use-case.
from minari.
Thanks for the response! Regarding the development of the streaming dataset backend, is this currently in a public fork? Curious to just to take a look and see if I could patch together something similar in the mean time before this becomes an official feature.
from minari.
Related Issues (20)
- looks strange for typing_extensions==4.4.0 HOT 1
- [Proposal] Humanoid Offline RL data HOT 4
- [Bug Report] Pre-commit error with gymnasium HOT 1
- [Proposal] Porting Antmazes to Minari. HOT 3
- [Proposal] Tests should not leave leftovers
- [Question] How to load RL step data in order HOT 1
- [Question] An easy recipe for DataCollector on Vectorized Envs? HOT 1
- [Proposal] Assertion error when obs and act is out of space, is this not too hard? Perhaps and warn instead? HOT 3
- [Fix] This line should be updated for gymnasium 1.0.0 HOT 2
- [Question] Does not iterating over episodes should produce "all" the episode data including infos and other stores keys? HOT 2
- [Question] Can recover_environment set render_mode attribute? HOT 2
- [Bug Report] Infos in existing dataset lost reset info. HOT 1
- [Question] Compatibility with PettingZoo HOT 2
- [Bug Report] step and info structures expected to be identical (when `record_infos=True`) HOT 1
- [Question] step and info structures expected to be identical (when `record_infos=True`)
- [Question] Citation for Minari HOT 1
- [Bug Report] Black render image HOT 4
- [Bug Report] Incorrect observation shape in some antmaze-umaze-v0 episodes HOT 2
- [Bug Report] listed datasets are unavailable for a given version - why list them? HOT 3
- [Bug Report] Misconfigured dataset on remote HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from minari.