serving

Hi all!
I am trying a self-play based scheme, where I want to have two agents in waterworld environment have a policy that is being trained (“shared_policy_1”) and other 3 agents that sample a policy from a menagerie (set) of the previous policies of the first two agents ( “shared_policy_2”).
My problem is that I see that the weights in the menagerie are overwritten in every iteration by the cur

... to make it easier to read Vespa documentation on an e-reader / offline

Vespa documentation is generated using Jekyll from .md and .html files, look into options for generating the artifact as part of site generation (there might be plugins we can use here)

For SC Operator it may be a good idea to generate CRD manifests from inside a docker container.
This should provide reproducible generation step and avoid "produces different output on my machine" issues.

Linter should also fail if generation of manifests produce diff with the commited version.

ReloadableInferEngine::proc_initialize中使用TaskExecutor的是个单例，那么多个模型会一次去设置、启动同一个TaskExecutor；
在调用schedule()之后，TaskExecutor如何确定去调用哪个模型呢？