{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:L53CRBNRVR3QECQ5IUN5HYXQ5Y","short_pith_number":"pith:L53CRBNR","canonical_record":{"source":{"id":"2004.06089","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-04-13T17:49:29Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"bb213405f1362fe8e6ca481e88c2f91c6f43a0ffe3d0169e5070deba01b10a93","abstract_canon_sha256":"16c9d24a1e884d78f9b1a25b8f650f89fbdc6a4eefd74762036a021c40ca0fe1"},"schema_version":"1.0"},"canonical_sha256":"5f762885b1ac77020a1d451bd3e2f0ee2cbd9a672db89a339bd1f2bf11091bac","source":{"kind":"arxiv","id":"2004.06089","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.06089","created_at":"2026-07-05T00:58:09Z"},{"alias_kind":"arxiv_version","alias_value":"2004.06089v4","created_at":"2026-07-05T00:58:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.06089","created_at":"2026-07-05T00:58:09Z"},{"alias_kind":"pith_short_12","alias_value":"L53CRBNRVR3Q","created_at":"2026-07-05T00:58:09Z"},{"alias_kind":"pith_short_16","alias_value":"L53CRBNRVR3QECQ5","created_at":"2026-07-05T00:58:09Z"},{"alias_kind":"pith_short_8","alias_value":"L53CRBNR","created_at":"2026-07-05T00:58:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:L53CRBNRVR3QECQ5IUN5HYXQ5Y","target":"record","payload":{"canonical_record":{"source":{"id":"2004.06089","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-04-13T17:49:29Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"bb213405f1362fe8e6ca481e88c2f91c6f43a0ffe3d0169e5070deba01b10a93","abstract_canon_sha256":"16c9d24a1e884d78f9b1a25b8f650f89fbdc6a4eefd74762036a021c40ca0fe1"},"schema_version":"1.0"},"canonical_sha256":"5f762885b1ac77020a1d451bd3e2f0ee2cbd9a672db89a339bd1f2bf11091bac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:09.647945Z","signature_b64":"Nr4smERup9Ng19JDE1lc7UVVC9Db73Ss+HAmBUef3rG3AAFW5/8fi3oO2AOCZHB5LVEFwR+tGJQ0/dCPPj9sDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f762885b1ac77020a1d451bd3e2f0ee2cbd9a672db89a339bd1f2bf11091bac","last_reissued_at":"2026-07-05T00:58:09.647443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:09.647443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.06089","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:58:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lE8lm8YSPXshXFR011z8kUd9Bg4v6GlxRyzWULFMPX3gLaA+Dawuvwvn2b1TLXRwb3lfDerye6t/K6yjTBSFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:57:27.516363Z"},"content_sha256":"4600248555153f6d6ebf2fe893113e71390e5c1fee67b35ad1a408aa45b6506b","schema_version":"1.0","event_id":"sha256:4600248555153f6d6ebf2fe893113e71390e5c1fee67b35ad1a408aa45b6506b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:L53CRBNRVR3QECQ5IUN5HYXQ5Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Thinking While Moving: Deep Reinforcement Learning with Concurrent Control","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Herzog, Dmitry Kalashnikov, Eric Jang, Julian Ibarz, Karol Hausman, Sergey Levine, Ted Xiao","submitted_at":"2020-04-13T17:49:29Z","abstract_excerpt":"We study reinforcement learning in settings where sampling an action from the policy must be done concurrently with the time evolution of the controlled system, such as when a robot must decide on the next action while still performing the previous action. Much like a person or an animal, the robot must think and move at the same time, deciding on its next action before the previous one has completed. In order to develop an algorithmic framework for such concurrent control problems, we start with a continuous-time formulation of the Bellman equations, and then discretize them in a way that is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06089","kind":"arxiv","version":4},"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/2004.06089/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:58:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mttn46ufkzuL7UE/YRDWab927C1/XpFbJLV9Ip85s/al6dMfIEGFfuag44qaKS/6yQV2/jghhlzGt0ZEBZoxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:57:27.516747Z"},"content_sha256":"1b6b6f588aecdde3f5de63296354087697cf14536e67d1df83c4902ce2dbcec0","schema_version":"1.0","event_id":"sha256:1b6b6f588aecdde3f5de63296354087697cf14536e67d1df83c4902ce2dbcec0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L53CRBNRVR3QECQ5IUN5HYXQ5Y/bundle.json","state_url":"https://pith.science/pith/L53CRBNRVR3QECQ5IUN5HYXQ5Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L53CRBNRVR3QECQ5IUN5HYXQ5Y/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T21:57:27Z","links":{"resolver":"https://pith.science/pith/L53CRBNRVR3QECQ5IUN5HYXQ5Y","bundle":"https://pith.science/pith/L53CRBNRVR3QECQ5IUN5HYXQ5Y/bundle.json","state":"https://pith.science/pith/L53CRBNRVR3QECQ5IUN5HYXQ5Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L53CRBNRVR3QECQ5IUN5HYXQ5Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:L53CRBNRVR3QECQ5IUN5HYXQ5Y","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"16c9d24a1e884d78f9b1a25b8f650f89fbdc6a4eefd74762036a021c40ca0fe1","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-04-13T17:49:29Z","title_canon_sha256":"bb213405f1362fe8e6ca481e88c2f91c6f43a0ffe3d0169e5070deba01b10a93"},"schema_version":"1.0","source":{"id":"2004.06089","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.06089","created_at":"2026-07-05T00:58:09Z"},{"alias_kind":"arxiv_version","alias_value":"2004.06089v4","created_at":"2026-07-05T00:58:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.06089","created_at":"2026-07-05T00:58:09Z"},{"alias_kind":"pith_short_12","alias_value":"L53CRBNRVR3Q","created_at":"2026-07-05T00:58:09Z"},{"alias_kind":"pith_short_16","alias_value":"L53CRBNRVR3QECQ5","created_at":"2026-07-05T00:58:09Z"},{"alias_kind":"pith_short_8","alias_value":"L53CRBNR","created_at":"2026-07-05T00:58:09Z"}],"graph_snapshots":[{"event_id":"sha256:1b6b6f588aecdde3f5de63296354087697cf14536e67d1df83c4902ce2dbcec0","target":"graph","created_at":"2026-07-05T00:58:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.06089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study reinforcement learning in settings where sampling an action from the policy must be done concurrently with the time evolution of the controlled system, such as when a robot must decide on the next action while still performing the previous action. Much like a person or an animal, the robot must think and move at the same time, deciding on its next action before the previous one has completed. In order to develop an algorithmic framework for such concurrent control problems, we start with a continuous-time formulation of the Bellman equations, and then discretize them in a way that is ","authors_text":"Alexander Herzog, Dmitry Kalashnikov, Eric Jang, Julian Ibarz, Karol Hausman, Sergey Levine, Ted Xiao","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-04-13T17:49:29Z","title":"Thinking While Moving: Deep Reinforcement Learning with Concurrent Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06089","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4600248555153f6d6ebf2fe893113e71390e5c1fee67b35ad1a408aa45b6506b","target":"record","created_at":"2026-07-05T00:58:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"16c9d24a1e884d78f9b1a25b8f650f89fbdc6a4eefd74762036a021c40ca0fe1","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-04-13T17:49:29Z","title_canon_sha256":"bb213405f1362fe8e6ca481e88c2f91c6f43a0ffe3d0169e5070deba01b10a93"},"schema_version":"1.0","source":{"id":"2004.06089","kind":"arxiv","version":4}},"canonical_sha256":"5f762885b1ac77020a1d451bd3e2f0ee2cbd9a672db89a339bd1f2bf11091bac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f762885b1ac77020a1d451bd3e2f0ee2cbd9a672db89a339bd1f2bf11091bac","first_computed_at":"2026-07-05T00:58:09.647443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:58:09.647443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nr4smERup9Ng19JDE1lc7UVVC9Db73Ss+HAmBUef3rG3AAFW5/8fi3oO2AOCZHB5LVEFwR+tGJQ0/dCPPj9sDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:58:09.647945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.06089","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4600248555153f6d6ebf2fe893113e71390e5c1fee67b35ad1a408aa45b6506b","sha256:1b6b6f588aecdde3f5de63296354087697cf14536e67d1df83c4902ce2dbcec0"],"state_sha256":"112c663fcff1c09e5925f4e879f8e9733924c7cd2ed84057341390a8393474e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0XQF+/fikxcrnxWDZObqkPT3wtUSAfLdhLXUphTXBczwUOS50b+iFhPHfzK6l3Xy3a+qhtqC4iPQNiyJhShhCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T21:57:27.519189Z","bundle_sha256":"8e23c0d2643bba9e86b0e5ca9882b083557faca5679625690e30c8742c06757c"}}