GitHub - SYCAMORE-1/ucb-MOPPO: implementation for UCB-driven Utility Function Search for Multi-objective Reinforcement Learning based on Decomposition

SYCAMORE-1 / ucb-MOPPO Public

Notifications You must be signed in to change notification settings
Fork 0
Star 1

implementation for UCB-driven Utility Function Search for Multi-objective Reinforcement Learning based on Decomposition

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 10 Commits
doc		doc
environments		environments
results		results
script		script
Dockerfile		Dockerfile
Readme.txt		Readme.txt
command.txt		command.txt

Repository files navigation

To run the proposed method and baselines on Mujoco V2, you need to run on linux kernal, 
follow the command.txt to build a independed docker environment on windows.

To run the proposed method on lasted Mujoco-V4, pip install gymnasium and follow the lastest apis on 
https://gymnasium.farama.org/environments/mujoco/

to run proposed methods on different problems with different seeds:
python ucb.py --eidx 0 --sidx 0