Sociarl
- 0 Collaborators
Societal problems are complex. The aim of the project is to utilize reinforcement learning for policy makers to observe how the utilities (rewards) introduced to people (agents) will affect the society (environment). ...learn more
Project status: Under Development
Game Development, Artificial Intelligence
Intel Technologies
AI DevCloud / Xeon,
Intel Opt ML/DL Framework
Overview / Usage
Aim of the project is to create a framework for the policy makers to evaluate how affective their strategy on solving a societal problem is. Currently, a Python based library to conduct Deep Reinforcement Learning based multi-agent experiments is being developed, like Gym but for multi-agent settings.
Methodology / Approach
Currently Deep Q-Learning based models are utilized by the agents and their global scale patterns emerged from the individual behaviors are observed.
Technologies Used
Hardware: Intel AI DevCloud
Software: Numpy, Matplotlib, PyTorch