Timothy Kassis
|
b8c4d2bae1
|
Add support for PufferLib which is a high-performance, open-source Python toolkit that wraps complex RL environments to look like standard Gym/PettingZoo interfaces and supports massively parallel simulation (1M+ steps/sec) to accelerate deep reinforcement learning.
|
2025-11-02 14:52:06 -08:00 |
|