Comments (2)
Hi Krishna,
Thanks for your interest in our work. For the finance environment, we provide up to 1000 trajectories of training data, which is roughly 2M transitions. You can change train_num=1000
in get_dataset
to get the full dataset. The dataset is already quite large in our sense, but in case you really need to generate more data, use can use the get_data.py
in our repo to do that.
To convert our data to d4rl format, you just need to map the keys, e.g. obs
-> observations
. Besides, we use index
to mark the end of each trajectories, you should convert that to timeouts
in a proper way.
from neorl.
Brilliant, 2M is good enough to get me started, thank you very much ! Cheers, and thanks for the great paper and code !
Krishna
from neorl.
Related Issues (11)
- Question regarding the dynamics pre-training HOT 2
- Question regarding the reward of sales promotion training dataset HOT 3
- Expert scores & random scores for normalization HOT 2
- Baseline Policies and Raw Results HOT 2
- LSTM HOT 1
- Next_Observation and Reward clamping in MOPO HOT 2
- Unable to reproduce results for BCQ
- Update Aim version and add Aim running instructions on README HOT 1
- Action space difference between datasset and environment HOT 2
- Learning curves in IB HOT 1
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 neorl.