View Code? Open in Web Editor
NEW
Implementation Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm in keras
License: MIT License
maddpg-keras's Introduction
๐ Hi, Iโm Prashant Shukla
๐ Iโm ML Engineer with 3 year experience
๐ฑ Iโm interested in Cognitive Science and AI
๐๏ธ My area of expertise is Statistics, NLP, Reinforcement Learning, Graph ML, Computer Vision
๐ซ You can reach me on my Email: [email protected]
maddpg-keras's People
Contributors
Watchers
maddpg-keras's Issues
While updating train.py
for flexible number of agents, updating of prev_state
to new_state
was deleted by mistake
Update code to restore updating of prev_state
Currently this implementation supports only 3 agents during training, with this enhancement it can support any number of agents decided by user during training
Seperate train and predict files in different folders
Add logic of codes in comments, to enable understanding of implementation for new user
Add docstrings to each functions