Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

checkpoint: File edit:

rUv7968cff10268
diff --git a/v3/@claude-flow/neural/__tests__/algorithms.test.ts b/v3/@claude-flow/neural/__tests__/algorithms.test.ts
index 37b270dafb..b2c451bcfc 100644
--- a/v3/@claude-flow/neural/__tests__/algorithms.test.ts
+++ b/v3/@claude-flow/neural/__tests__/algorithms.test.ts
@@ -393,7 +393,8 @@ describe('PPO Algorithm', () => {
const result = ppo.update();
- expect(result.policyLoss).toBeGreaterThanOrEqual(0);
+ // Policy loss can be negative in PPO (we minimize -surrogate_objective)
+ expect(typeof result.policyLoss).toBe('number');
expect(result.valueLoss).toBeGreaterThanOrEqual(0);
expect(result.entropy).toBeGreaterThanOrEqual(0);
});