Yifan Yang 9379e494bf docs(sleep): document the controllable dreaming architecture ...

Captures the four-stage refactor: train(dream)/val(real)/test(real) splits,
optional gate, gate-independent slow-update long-term memory, token/time budget,
multi-rollout contrastive reflection, multi-objective reward (accuracy/tokens/
latency), and user-preference priors — with a one-command example composing them.

Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>

2026-06-08 14:31:51 +00:00

..

guide

docs: align API reference and Add-a-Benchmark guide with real EnvAdapter ABC

2026-06-01 20:14:54 +00:00

reference

docs: align API reference and Add-a-Benchmark guide with real EnvAdapter ABC

2026-06-01 20:14:54 +00:00

sleep

docs(sleep): document the controllable dreaming architecture

2026-06-08 14:31:51 +00:00

superpowers/specs

docs: add SkillOpt-Sleep Claude Code plugin design

2026-06-08 14:31:51 +00:00

contributing.md

SkillOpt v0.1.0: initial release

2026-05-21 17:22:04 +00:00

index.md

refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update

2026-05-24 19:15:10 +00:00