Spaces:
Sleeping
Sleeping
| spec_version: 1 | |
| name: rail_ops | |
| type: space | |
| runtime: fastapi | |
| app: rail_openenv.server:app | |
| port: 7860 | |
| description: Rail dispatch on Arriva's single-track Groningen - Leeuwarden line (Netherlands) on real January-June 2025 days - hold, short-turn and cancel trains so opposing trains cross safely after real breakdowns, collisions, signal and points failures (and seeded ones drawn from the 2024-2025 disruption record); graded once on submit against the CP-SAT optimum. 45 eval tasks on held-out weeks, chosen for hardness, and a train pack on the other days. | |
| version: "0.1.0" | |
| variables: | |
| RAIL_TASKS_DIR: "" # colon-separated pack directories; defaults to tasks/rail-v1-eval:tasks/rail-v1-train | |
| RAIL_MAX_CHECKS: "10" | |
| RAIL_MAX_TOOL_CALLS: "24" | |
| MAX_CONCURRENT_ENVS: "64" | |
| validation: | |
| reward: | |
| range: [0.0, 1.0] | |
| # oracle/solve.py submits the CP-SAT optimum and scores exactly 1.0; no plan scores 0, any rule broken < 0.2 | |
| oracle_tolerance: 0.001 | |
| floor_margin: 0.5 | |
| resources: | |
| # pure Python: the grader re-simulates a plan in milliseconds, CP-SAT never runs on the server | |
| cpu: 2.0 | |
| memory_mb: 2048 | |
| disk_mb: 1024 | |
| episode_timeout_s: 3600.0 | |
| network: | |
| mode: no-network | |
| capabilities: | |
| verifier: | |
| kind: reward_channel | |
| oracle: | |
| form: script | |
| location: oracle/solve.py | |
| rubric_tree: true | |
| task_api: true | |
| declared_tools: [get_situation, check_plan, submit_plan] | |
| types: | |
| tags: [simulation, railway, dispatching, scheduling, operations-research, mcp, real-world-data] | |