search

LucasAlegre / morl-baselines

Multi-Objective Reinforcement Learning algorithms implementations.
https://lucasalegre.github.io/morl-baselines
MIT License
271 stars 44 forks source link

Visualizing the generated Pareto front #73

Closed xwen24 closed 9 months ago

xwen24 commented 10 months ago

Hello, thanks so much for sharing the codes!

I am a beginner in multi-objective reinforcement learning and would like to apply CAPQL in my domain. I have three questions:

(1) is the CAPQL code able to optimize three or more objectives currently? (2) how to visualize the finally generated Pareto front? (3) it that possible to visualize the Pareto front with three objectives?

LucasAlegre commented 10 months ago

(1) Yes. (2) We use weights and biases to log the Pareto front. There you can visualize it as a table or as a 2d plot. (3) We don't know how to do it in weights and biases yet. But you can download the Pareto front from weights and biases and use your favorite Python plotting library to visualize it locally.

ffelten commented 10 months ago

@xwen24 is this solved?

xwen24 commented 10 months ago

Sorry for the late reply.

Thanks so much for your help! My porblme has been solved.

xwen24 commented 9 months ago

Sorry to bother your again. I am just wondering if you plan to add more MORL algorithms in the future, such as "Distributional Pareto-Optimal Multi-Objective Reinforcement Learning" by Cai et al. in NeurIPS 2023.

ffelten commented 9 months ago

Hi @xwen24,

Unfortunately, on my side I will not have time to do this in the following months but maybe later next year. However, in the meanwhile we are always happy to receive new contributions :-).