Comments (2)
Suggestion
These config files could be used by a ConfigManager
that can translate in both directions between a YAML (or JSON?) file and the actual ConfigTuple
used to create a TrialRunner
at runtime. Experiment config files could just be concatenations of trial configs with some additional logic to reduce redundancy (e.g. specifying repeated trials with different seeds, experiment-wide CPU/GPU allocations, etc.). The ConfigManager
could also cooperate with individual IOManagers
to save config files alongside data generated during experiments.
from costaware.
Created YAML formats for specifying trials as well as more general experiments, which are collections of potentially distinct trial types. Created examples scripts demonstrating that they work and showing how to use them.
from costaware.
Related Issues (20)
- Ratio computation
- Get DeepACAgent working on cost-aware gym envs
- Get deep RL agents working on portfolio problem
- Gaussian policy
- Get ExperimentRunner working with deep RL agents
- Plotter requires working LaTeX installation HOT 1
- Plotter handles some experiments inappropriately HOT 2
- Agents should be initialized with envs
- A proper linear softmax policy HOT 1
- Merge experiments into master
- Make a publication branch (out of deep experiments branch)
- Combine deep and synthetic MDP code into one branch HOT 2
- Get rid of all extraneous stuff HOT 2
- Make some nice example scripts to help people understand the code and paper results HOT 2
- Make a nice README and choose an appropriate license HOT 1
- OPTIONAL: add nice graphics/videos to illustrate things
- Renaming HOT 1
- Rearrangements HOT 1
- Documentation!
- Make `publication` branch into `master`; delete `dev` and `plotting` branches HOT 2
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 costaware.