search

instadeepai / Mava

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX
Apache License 2.0
739 stars 91 forks source link

Add Softmax with Regularization functionality for QMIX style algorithms. #156

Closed sgrimbly closed 3 years ago

sgrimbly commented 3 years ago

https://arxiv.org/abs/2103.11883v1

sgrimbly commented 3 years ago

Have read the paper. Looks good! Well worth adding.