{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7J3SU7LLV6O6QQ2J2RUIFTBIDX","short_pith_number":"pith:7J3SU7LL","schema_version":"1.0","canonical_sha256":"fa772a7d6baf9de84349d46882cc281de51a5e471a70c6a052f873258d687162","source":{"kind":"arxiv","id":"2606.26463","version":1},"attestation_state":"computed","paper":{"title":"Finding the Time to Think: Learning Planning Budgets in Real-Time RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aneesh Muppidi, Dylan Cope, Firas Darwish, Jakob Nicolaus Foerster, Jo\\~ao F. Henriques","submitted_at":"2026-06-24T23:55:15Z","abstract_excerpt":"Deliberating takes time. In real-time settings, that time is not free. Standard reinforcement learning (RL) sidesteps this as the environment waits indefinitely for the agent's decision. Instead, we study real-time RL environments where the environment progresses while waiting for the agent's action. Building on prior real-time formalizations, we introduce variable-delay real-time RL, where the agent chooses how long to deliberate at each decision point since the environment progresses. For the planning agents we use, the right delay is state-dependent, and naively planning how long to plan ca"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.26463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T23:55:15Z","cross_cats_sorted":[],"title_canon_sha256":"600b4294ddd27c70510a1df70a1fb2a2d3f9a0086fe2915d69c20085b9a17843","abstract_canon_sha256":"554bf99c5b19d8994c8023da2f9070e6bb3dfbbf766933c5cc82294048548ab9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:31.898274Z","signature_b64":"gQJiLzAvS1sqX5lr+KeIv/s+IYqpqti34xMQw2YFTwdLUJjrIZPEcA6uaM0B1inSFifQxF21klrbATeDQNLqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa772a7d6baf9de84349d46882cc281de51a5e471a70c6a052f873258d687162","last_reissued_at":"2026-06-26T01:15:31.897757Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:31.897757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding the Time to Think: Learning Planning Budgets in Real-Time RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aneesh Muppidi, Dylan Cope, Firas Darwish, Jakob Nicolaus Foerster, Jo\\~ao F. Henriques","submitted_at":"2026-06-24T23:55:15Z","abstract_excerpt":"Deliberating takes time. In real-time settings, that time is not free. Standard reinforcement learning (RL) sidesteps this as the environment waits indefinitely for the agent's decision. Instead, we study real-time RL environments where the environment progresses while waiting for the agent's action. Building on prior real-time formalizations, we introduce variable-delay real-time RL, where the agent chooses how long to deliberate at each decision point since the environment progresses. For the planning agents we use, the right delay is state-dependent, and naively planning how long to plan ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26463","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.26463/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.26463","created_at":"2026-06-26T01:15:31.897817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26463v1","created_at":"2026-06-26T01:15:31.897817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26463","created_at":"2026-06-26T01:15:31.897817+00:00"},{"alias_kind":"pith_short_12","alias_value":"7J3SU7LLV6O6","created_at":"2026-06-26T01:15:31.897817+00:00"},{"alias_kind":"pith_short_16","alias_value":"7J3SU7LLV6O6QQ2J","created_at":"2026-06-26T01:15:31.897817+00:00"},{"alias_kind":"pith_short_8","alias_value":"7J3SU7LL","created_at":"2026-06-26T01:15:31.897817+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7J3SU7LLV6O6QQ2J2RUIFTBIDX","json":"https://pith.science/pith/7J3SU7LLV6O6QQ2J2RUIFTBIDX.json","graph_json":"https://pith.science/api/pith-number/7J3SU7LLV6O6QQ2J2RUIFTBIDX/graph.json","events_json":"https://pith.science/api/pith-number/7J3SU7LLV6O6QQ2J2RUIFTBIDX/events.json","paper":"https://pith.science/paper/7J3SU7LL"},"agent_actions":{"view_html":"https://pith.science/pith/7J3SU7LLV6O6QQ2J2RUIFTBIDX","download_json":"https://pith.science/pith/7J3SU7LLV6O6QQ2J2RUIFTBIDX.json","view_paper":"https://pith.science/paper/7J3SU7LL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26463&json=true","fetch_graph":"https://pith.science/api/pith-number/7J3SU7LLV6O6QQ2J2RUIFTBIDX/graph.json","fetch_events":"https://pith.science/api/pith-number/7J3SU7LLV6O6QQ2J2RUIFTBIDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7J3SU7LLV6O6QQ2J2RUIFTBIDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7J3SU7LLV6O6QQ2J2RUIFTBIDX/action/storage_attestation","attest_author":"https://pith.science/pith/7J3SU7LLV6O6QQ2J2RUIFTBIDX/action/author_attestation","sign_citation":"https://pith.science/pith/7J3SU7LLV6O6QQ2J2RUIFTBIDX/action/citation_signature","submit_replication":"https://pith.science/pith/7J3SU7LLV6O6QQ2J2RUIFTBIDX/action/replication_record"}},"created_at":"2026-06-26T01:15:31.897817+00:00","updated_at":"2026-06-26T01:15:31.897817+00:00"}