Comments (3)
Hi @omidsbhn,
Thank you for the bug report :-)!
Indeed, it seems there is something off there. One (or more) bug might have slipped in, we didn't thoroughly tested this algorithm yet tbh.
I tried to use squeeze and compare to the current implementation, can't say it changes much (green is fixed, purple is current implem):
I would appreciate it we keep digging on this and discuss the implementation if you want :-)
from morl-baselines.
Hi @ffelten
Thank you for checking the issue so quickly :-)
For me the graphs are almost the same, but I think for more complex environments, it could be an issue.
Btw, I would be happy to discuss the implementation and keep digging on this. Specifically, based on this implementation I'm trying to regenerate the ablation study suggested by the paper.
from morl-baselines.
You can join the discord for direct communication https://discord.com/invite/jpYmEFNT
from morl-baselines.
Related Issues (20)
- Error when running CAPQL-based algorithm on Hopper HOT 4
- Help Regarding Interpreting PGMORL Convergence HOT 2
- Multi-core Training PGMORL
- Pareto Q-Learning fails with any environment that doesn't have 2D state/obs space HOT 6
- Help Regarding GPILSContinuousAction Model Convergence HOT 10
- The Pareto front generated by minecart is not optimal HOT 1
- Visualizing the generated Pareto front HOT 5
- Using mo-highway environment with morl baselines HOT 2
- Does anyone know how to load the trained model? HOT 3
- how to run the file named gpi_pd_hopper.py in the example folder? HOT 2
- Bug in PCN due to logging HOT 1
- Why is PCN only working for deterministic envs? HOT 4
- AttributeError: module 'cdd' has no attribute 'Matrix' HOT 3
- Evaluation of the generated Pareto front HOT 2
- Missing instructions on how to train CAPQL agent HOT 1
- Multi Discrete action space HOT 3
- why do the GPI-LS and GPI-PD run for a very long time? HOT 4
- Offline Training HOT 1
- Implementation of MOPPO fails 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 morl-baselines.