{"uid":"cap_DgDq39X7mKUb_8bic3wdu","slug":"cloud-world-model-rl-batch-step-2faf1b65","name":"Cloud World Model RL Batch Step","description":"Execute multiple RL training actions in a single request (up to 30 steps per call).","url":"https://www.cloudworldmodel.ai/api/rl/environments/f7b5d7c8-1fae-4ef1-a703-e7861a94324e/batch-step","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"steps":{"type":"array","items":{"type":"object","required":["action"],"properties":{"action":{"type":"object","required":["type"],"properties":{"type":{"enum":["adjust_threshold","scale_out","scale_in","add_resource","remove_resource","no_op","set_recovery_policy"],"type":"string"},"parameters":{"type":"object","additionalProperties":true}}},"tick_seconds":{"type":"integer","maximum":3600,"minimum":1,"description":"Simulated seconds per step (overrides environment default)"}}},"maxItems":30,"minItems":1,"description":"Ordered list of step actions to execute (max 30)"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_COwNmHp0U8Qm92PIlYIEq","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Execute up to 30 reinforcement learning training actions in a single batch request against a specific cloud simulation environment.","exampleAgentPrompt":"Run a batch of 10 RL training steps on environment 57dc6e63-8a05-47cb-832f-db07aa1dc877 — first scale_out twice, then adjust_threshold with a target CPU of 70, then do no_op for 5 steps, and finally scale_in once, each step simulating 60 seconds of cloud time.","exampleUseCases":null,"resultDescription":"Returns the results of all executed steps in the batch, including updated environment state, observations, rewards, and any transition data produced by the hybrid cloud simulation engine after each action in the ordered sequence.","failureModes":["More than 30 steps provided — request rejected with validation error","Invalid action type not in enum (adjust_threshold, scale_out, scale_in, add_resource, remove_resource, no_op, set_recovery_policy)","tick_seconds out of range (must be 1–3600)","Environment ID not found or not accessible","Payment not attached or insufficient USDC — 402 payment required","Empty steps array — minItems 1 violated","Malformed action parameters object"],"whenToPreferThis":"Use this endpoint when you need to advance an RL training environment by multiple timesteps efficiently without making a separate API call per step. It is preferred over the single-step endpoint when running training loops, evaluating long action sequences, or batching simulation steps for throughput — saving both latency and per-call costs (up to 30x operations per $0.001).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:39:15.568Z","isFirstParty":false}