Spaces:
Sleeping
Sleeping
Commit History
-
Harden reward boundary handling
aa0019f
-
Initial submission: Avigilance 2.0 — India Aviation Safety Monitoring OpenEnv
Three-task OpenEnv for DGCA aviation safety oversight: - Task 1: FTO Quality Scorer (mean=0.8190, 100 episodes) - Task 2: Incident Prioritiser (mean=0.5358, 100 episodes) - Task 3: Resource Allocator (mean=0.8380, 10 episodes) LLM agent with rolling memory and multi-model free fallback pool. Grounded in MGURM framework with P1/P2/P3 safety principles. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>fe073e2
