The Eval Index / Observability / #80
Sheltercosmo/Rilldex-RL-Studio
by Sheltercosmo · Observability · updated 2d ago
RL observability for LLM agents: behavior maps, native trainer metrics, rollout investigations, and Python/SQL analysis.
65
momentum
80
stars
17
forks
#80
rank
agent-observabilityagentic-rlexperiment-trackinggrpollm-debuggingllm-observabilitypost-trainingreinforcement-learningreward-hackingrlhfrlvrtraining-monitoring
View on GitHub →