{ "task": "hard_multi", "seed": 3, "policy": "ppo", "episode_length": 20, "total_reward": 9.4544, "grader": { "overall_score": 0.7514, "success_score": 0.8, "latency_score": 0.7388, "budget_score": 0.0909, "sla_score": 1.0, "adaptation_score": 1.0 }, "metrics": { "total_reward": 9.4545, "success_rate": 1.0, "total_cost_spent": 1.0, "average_latency_ms": 130.62, "sla_met": true, "queue_overflow_events": 0 }, "steps": [ { "step": 1, "action": "route_to_b", "provider": "B", "success": true, "reward": 0.7727, "cumulative_reward": 0.7727, "cost": 0.05, "budget_remaining": 1.05, "latency_ms": 136.82, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 0.5, "provider_c_status": 0.5, "observed_budget_remaining": 1.0, "queue_backlog": 0.0, "system_latency": 0.2, "step_count": 0.0 }, { "step": 2, "action": "route_to_b", "provider": "B", "success": true, "reward": 0.7727, "cumulative_reward": 1.5455, "cost": 0.05, "budget_remaining": 1.0, "latency_ms": 136.92, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 0.5, "observed_budget_remaining": 0.9545, "queue_backlog": 0.0, "system_latency": 0.2736, "step_count": 0.05 }, { "step": 3, "action": "route_to_b", "provider": "B", "success": true, "reward": 0.7727, "cumulative_reward": 2.3182, "cost": 0.05, "budget_remaining": 0.95, "latency_ms": 116.96, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 0.5, "observed_budget_remaining": 0.9091, "queue_backlog": 0.0, "system_latency": 0.2738, "step_count": 0.1 }, { "step": 4, "action": "route_to_b", "provider": "B", "success": true, "reward": 0.7727, "cumulative_reward": 3.0909, "cost": 0.05, "budget_remaining": 0.9, "latency_ms": 148.46, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 0.5, "observed_budget_remaining": 0.8636, "queue_backlog": 0.0, "system_latency": 0.2339, "step_count": 0.15 }, { "step": 5, "action": "route_to_b", "provider": "B", "success": true, "reward": 0.7727, "cumulative_reward": 3.8636, "cost": 0.05, "budget_remaining": 0.85, "latency_ms": 160.57, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 0.5, "observed_budget_remaining": 0.8182, "queue_backlog": 0.0, "system_latency": 0.2969, "step_count": 0.2 }, { "step": 6, "action": "route_to_b", "provider": "B", "success": true, "reward": 0.7727, "cumulative_reward": 4.6364, "cost": 0.05, "budget_remaining": 0.8, "latency_ms": 74.57, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 0.5, "observed_budget_remaining": 0.7727, "queue_backlog": 0.0, "system_latency": 0.3211, "step_count": 0.25 }, { "step": 7, "action": "route_to_b", "provider": "B", "success": true, "reward": 0.7727, "cumulative_reward": 5.4091, "cost": 0.05, "budget_remaining": 0.75, "latency_ms": 75.52, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 0.5, "observed_budget_remaining": 0.7273, "queue_backlog": 0.0, "system_latency": 0.1491, "step_count": 0.3 }, { "step": 8, "action": "route_to_b", "provider": "B", "success": true, "reward": 0.7727, "cumulative_reward": 6.1818, "cost": 0.05, "budget_remaining": 0.7, "latency_ms": 83.22, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 0.5, "observed_budget_remaining": 0.6818, "queue_backlog": 0.0, "system_latency": 0.151, "step_count": 0.35 }, { "step": 9, "action": "route_to_b", "provider": "B", "success": true, "reward": 0.7727, "cumulative_reward": 6.9545, "cost": 0.05, "budget_remaining": 0.65, "latency_ms": 169.39, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 0.5, "observed_budget_remaining": 0.6364, "queue_backlog": 0.0, "system_latency": 0.1664, "step_count": 0.4 }, { "step": 10, "action": "route_to_b", "provider": "B", "success": true, "reward": 0.7727, "cumulative_reward": 7.7273, "cost": 0.05, "budget_remaining": 0.6, "latency_ms": 49.24, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 0.5, "observed_budget_remaining": 0.5909, "queue_backlog": 0.0, "system_latency": 0.3388, "step_count": 0.45 }, { "step": 11, "action": "route_to_b", "provider": "B", "success": true, "reward": 0.7727, "cumulative_reward": 8.5, "cost": 0.05, "budget_remaining": 0.55, "latency_ms": 39.92, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 0.5, "observed_budget_remaining": 0.5455, "queue_backlog": 0.0, "system_latency": 0.0985, "step_count": 0.5 }, { "step": 12, "action": "route_to_b", "provider": "B", "success": true, "reward": 0.7727, "cumulative_reward": 9.2727, "cost": 0.05, "budget_remaining": 0.5, "latency_ms": 134.38, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 0.5, "observed_budget_remaining": 0.5, "queue_backlog": 0.0, "system_latency": 0.0798, "step_count": 0.55 }, { "step": 13, "action": "route_to_c", "provider": "C", "success": true, "reward": 0.5455, "cumulative_reward": 9.8182, "cost": 0.1, "budget_remaining": 0.4, "latency_ms": 170.39, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 0.5, "observed_budget_remaining": 0.4545, "queue_backlog": 0.0, "system_latency": 0.2688, "step_count": 0.6 }, { "step": 14, "action": "route_to_c", "provider": "C", "success": true, "reward": 0.5455, "cumulative_reward": 10.3636, "cost": 0.1, "budget_remaining": 0.3, "latency_ms": 197.75, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 1.0, "observed_budget_remaining": 0.3636, "queue_backlog": 0.0, "system_latency": 0.3408, "step_count": 0.65 }, { "step": 15, "action": "shed_load", "provider": null, "success": false, "reward": -0.5, "cumulative_reward": 9.8636, "cost": 0.0, "budget_remaining": 0.3, "latency_ms": 0.0, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 1.0, "observed_budget_remaining": 0.2727, "queue_backlog": 0.0, "system_latency": 0.3955, "step_count": 0.7 }, { "step": 16, "action": "route_to_c", "provider": "C", "success": true, "reward": 0.5455, "cumulative_reward": 10.4091, "cost": 0.1, "budget_remaining": 0.2, "latency_ms": 295.11, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 1.0, "observed_budget_remaining": 0.2727, "queue_backlog": 0.0, "system_latency": 0.0, "step_count": 0.75 }, { "step": 17, "action": "shed_load", "provider": null, "success": false, "reward": -0.5, "cumulative_reward": 9.9091, "cost": 0.0, "budget_remaining": 0.2, "latency_ms": 0.0, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 1.0, "observed_budget_remaining": 0.1818, "queue_backlog": 0.0, "system_latency": 0.5902, "step_count": 0.8 }, { "step": 18, "action": "route_to_c", "provider": "C", "success": true, "reward": 0.5455, "cumulative_reward": 10.4545, "cost": 0.1, "budget_remaining": 0.1, "latency_ms": 100.73, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 1.0, "observed_budget_remaining": 0.1818, "queue_backlog": 0.0, "system_latency": 0.0, "step_count": 0.85 }, { "step": 19, "action": "shed_load", "provider": null, "success": false, "reward": -0.5, "cumulative_reward": 9.9545, "cost": 0.0, "budget_remaining": 0.1, "latency_ms": 0.0, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 1.0, "observed_budget_remaining": 0.0909, "queue_backlog": 0.0, "system_latency": 0.2015, "step_count": 0.9 }, { "step": 20, "action": "shed_load", "provider": null, "success": false, "reward": -0.5, "cumulative_reward": 9.4545, "cost": 0.0, "budget_remaining": 0.1, "latency_ms": 0.0, "queue_overflow": false, "budget_exhausted": false, "provider_a_status": 0.5, "provider_b_status": 1.0, "provider_c_status": 1.0, "observed_budget_remaining": 0.0909, "queue_backlog": 0.0, "system_latency": 0.0, "step_count": 0.95 } ] }