Skip to content
/ IA2C Public

Code base in PyTorch for MARL method interactive A2C

License

Notifications You must be signed in to change notification settings

thinclab/IA2C

Repository files navigation

IA2C

Code for paper:

Keyang He, Bikramjit Banerjee, and Prashant Doshi. Cooperative-Competitive Reinforcement Learning with History-Dependent Rewards. In Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), pp. 602–610, 2021. https://sites.usm.edu/banerjee/papers/p602.pdf

Also part of paper:

Keyang He, Prashant Doshi, and Bikramjit Banerjee. Modeling and reinforcement learning in partially observable many-agent systems. In Autonomous Agents and Multi-Agent Systems, Vol. 38(12), Springer, 2024. https://rdcu.be/dCAeY

Actor-Critic network classes are in ac_nets.py. Code to test/use these classes are provided in a2c_test.py. IA2C code is in ia2c.py.

How to Run On Org Domain

Install requirements using command pip install -r requirements.txt

Ensure all files are in the same Directory

Then run command python a2c_org_test.py

About

Code base in PyTorch for MARL method interactive A2C

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages