search

decisionforce / CoPO

[NeurIPS 2021] Official implementation of paper "Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization".
Apache License 2.0
117 stars 20 forks source link

Code implementation #15

Closed Lucky-Lance closed 1 year ago

Lucky-Lance commented 2 years ago

Hello, your code is implemented with ray and tf. Can you please provide a copy with pytorch? Thanks.

pengzhenghao commented 2 years ago

Hi @Lucky-Lance , I am preparing a torch + RLLib version of CoPO and will release soon (probably next week).

pengzhenghao commented 1 year ago

Just for your information, the torch version of CoPO is implemented here: https://github.com/decisionforce/CoPO/tree/main/copo_code/copo/torch_copo

with ray==2.2.0