Comments (3)
@natashamjaques this might be a good thing for you to look into as its relatively parallel to implementing the environments? I'm happy to help you with rllib setup or point you to the right place in rllib for doing this. We can also just implement this using OpenAI Baselines which can be a little easier to manipulate.
from sequential_social_dilemma_games.
Confirmed that the reward postprocessing can be done in rllib's post_process_trajectory method:
see implementing a centralized critic part of:
https://ray.readthedocs.io/en/latest/rllib-env.html#multi-agent
in post-process trajectory you can query compute_action to do counterfactuals and then adjust the reward. Happily, this should be pretty easy!
from sequential_social_dilemma_games.
Moving this to other repo.
from sequential_social_dilemma_games.
Related Issues (20)
- How to know if the code is working correctly?
- Difficulties with setup HOT 2
- MIT License HOT 3
- implementation of the 'communication model' HOT 2
- Cleanup color map for 'Light grey-blue river cell' and 'brown waste cells' needs to be switched.
- Multiple policies in MOA training HOT 2
- Trouble getting train_baseline to work HOT 1
- i have som question
- Citation HOT 3
- Some errors when run "python -m pytest" HOT 8
- Some questions about "train_baseline.py"
- pytest fails despite correcting ray and tensorflow versions
- Observation and agent are rotating in the opposite directions
- Windows support HOT 1
- ray/result/exp is empty
- This library will break in a week when PZ is updated, (no version control)
- MapEnv - update_moves
- About the default number of agents
- Feature request: update PettingZoo version HOT 3
- Visualization using A3C agents in harvest env 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 sequential_social_dilemma_games.