mirror of
https://github.com/vale981/ray
synced 2025-03-08 19:41:38 -05:00
![]() This introduces rllib.Evaluator and rllib.Optimizer classes. Optimizers encapsulate a particular distributed optimization strategy for RL. Evaluators encapsulate the model graph, and once implemented, any Optimizer may be "plugged in" to any algorithm that implements the Evaluator interface. |
||
---|---|---|
.. | ||
ray | ||
build-wheel-macos.sh | ||
build-wheel-manylinux1.sh | ||
README-building-wheels.md | ||
setup.py |