{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:REOCPANT3KRBQA23H6CXA5QEU6","short_pith_number":"pith:REOCPANT","canonical_record":{"source":{"id":"1610.00673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-03T18:54:00Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"8ddb98d9b06f82ccc58bc8eec80c7e8619d4db8dabc891e27002889fbb49f4eb","abstract_canon_sha256":"41a4121abf71d08e0a83648a44cd172e608717f964a37ab796339d748c5ab142"},"schema_version":"1.0"},"canonical_sha256":"891c2781b3daa218035b3f85707604a7b05c4b8c0d3a70f27177ea8b361bbd80","source":{"kind":"arxiv","id":"1610.00673","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.00673","created_at":"2026-05-17T23:45:00Z"},{"alias_kind":"arxiv_version","alias_value":"1610.00673v1","created_at":"2026-05-17T23:45:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.00673","created_at":"2026-05-17T23:45:00Z"},{"alias_kind":"pith_short_12","alias_value":"REOCPANT3KRB","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"REOCPANT3KRBQA23","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"REOCPANT","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:REOCPANT3KRBQA23H6CXA5QEU6","target":"record","payload":{"canonical_record":{"source":{"id":"1610.00673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-03T18:54:00Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"8ddb98d9b06f82ccc58bc8eec80c7e8619d4db8dabc891e27002889fbb49f4eb","abstract_canon_sha256":"41a4121abf71d08e0a83648a44cd172e608717f964a37ab796339d748c5ab142"},"schema_version":"1.0"},"canonical_sha256":"891c2781b3daa218035b3f85707604a7b05c4b8c0d3a70f27177ea8b361bbd80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:00.361332Z","signature_b64":"1HFaNx11lW5DzwQ4Hwms270VxsuiVAx7pvtuzYMuw9QmiCXnmPX6sk6R8Hxl50SUTj69Kuy0EYCvvl9FnwRbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"891c2781b3daa218035b3f85707604a7b05c4b8c0d3a70f27177ea8b361bbd80","last_reissued_at":"2026-05-17T23:45:00.360680Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:00.360680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.00673","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kHsTVZOc+KM8bjsN+baqNZoHNcf3JlhNrmgr4B0Sv4PgpXF4yw14J7ARA5lJwgcky/QSm+/9PvGFWixQALBJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T01:59:35.220780Z"},"content_sha256":"1d416ff0ca1f21f43db4b02ee58be8178d764df8f3293e9c50d0d53d7aea7840","schema_version":"1.0","event_id":"sha256:1d416ff0ca1f21f43db4b02ee58be8178d764df8f3293e9c50d0d53d7aea7840"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:REOCPANT3KRBQA23H6CXA5QEU6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Adrian Li, Ali Yahya, Mrinal Kalakrishnan, Sergey Levine, Yevgen Chebotar","submitted_at":"2016-10-03T18:54:00Z","abstract_excerpt":"In principle, reinforcement learning and policy search methods can enable robots to learn highly complex and general skills that may allow them to function amid the complexity and diversity of the real world. However, training a policy that generalizes well across a wide range of real-world conditions requires far greater quantity and diversity of experience than is practical to collect with a single robot. Fortunately, it is possible for multiple robots to share their experience with one another, and thereby, learn a policy collectively. In this work, we explore distributed and asynchronous p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.00673","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":""},"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":"2026-05-17T23:45:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jwkD/8XdMlIi+S9AI+jsOxfekhzCj7gD6ckGRmEU4EsBEd3rurA2Bd9PKd4+IOc5OLXh6cu7QzytbtwDa2FoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T01:59:35.221127Z"},"content_sha256":"7649e58c3c64f623f541deb53a2f08ecd79141fcf81bd0e317b45fcc14d27931","schema_version":"1.0","event_id":"sha256:7649e58c3c64f623f541deb53a2f08ecd79141fcf81bd0e317b45fcc14d27931"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/REOCPANT3KRBQA23H6CXA5QEU6/bundle.json","state_url":"https://pith.science/pith/REOCPANT3KRBQA23H6CXA5QEU6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/REOCPANT3KRBQA23H6CXA5QEU6/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":"2026-06-03T01:59:35Z","links":{"resolver":"https://pith.science/pith/REOCPANT3KRBQA23H6CXA5QEU6","bundle":"https://pith.science/pith/REOCPANT3KRBQA23H6CXA5QEU6/bundle.json","state":"https://pith.science/pith/REOCPANT3KRBQA23H6CXA5QEU6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/REOCPANT3KRBQA23H6CXA5QEU6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:REOCPANT3KRBQA23H6CXA5QEU6","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":"41a4121abf71d08e0a83648a44cd172e608717f964a37ab796339d748c5ab142","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-03T18:54:00Z","title_canon_sha256":"8ddb98d9b06f82ccc58bc8eec80c7e8619d4db8dabc891e27002889fbb49f4eb"},"schema_version":"1.0","source":{"id":"1610.00673","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.00673","created_at":"2026-05-17T23:45:00Z"},{"alias_kind":"arxiv_version","alias_value":"1610.00673v1","created_at":"2026-05-17T23:45:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.00673","created_at":"2026-05-17T23:45:00Z"},{"alias_kind":"pith_short_12","alias_value":"REOCPANT3KRB","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"REOCPANT3KRBQA23","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"REOCPANT","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:7649e58c3c64f623f541deb53a2f08ecd79141fcf81bd0e317b45fcc14d27931","target":"graph","created_at":"2026-05-17T23:45:00Z","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"},"paper":{"abstract_excerpt":"In principle, reinforcement learning and policy search methods can enable robots to learn highly complex and general skills that may allow them to function amid the complexity and diversity of the real world. However, training a policy that generalizes well across a wide range of real-world conditions requires far greater quantity and diversity of experience than is practical to collect with a single robot. Fortunately, it is possible for multiple robots to share their experience with one another, and thereby, learn a policy collectively. In this work, we explore distributed and asynchronous p","authors_text":"Adrian Li, Ali Yahya, Mrinal Kalakrishnan, Sergey Levine, Yevgen Chebotar","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-03T18:54:00Z","title":"Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.00673","kind":"arxiv","version":1},"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":"sha256:1d416ff0ca1f21f43db4b02ee58be8178d764df8f3293e9c50d0d53d7aea7840","target":"record","created_at":"2026-05-17T23:45:00Z","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":"41a4121abf71d08e0a83648a44cd172e608717f964a37ab796339d748c5ab142","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-03T18:54:00Z","title_canon_sha256":"8ddb98d9b06f82ccc58bc8eec80c7e8619d4db8dabc891e27002889fbb49f4eb"},"schema_version":"1.0","source":{"id":"1610.00673","kind":"arxiv","version":1}},"canonical_sha256":"891c2781b3daa218035b3f85707604a7b05c4b8c0d3a70f27177ea8b361bbd80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"891c2781b3daa218035b3f85707604a7b05c4b8c0d3a70f27177ea8b361bbd80","first_computed_at":"2026-05-17T23:45:00.360680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:00.360680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1HFaNx11lW5DzwQ4Hwms270VxsuiVAx7pvtuzYMuw9QmiCXnmPX6sk6R8Hxl50SUTj69Kuy0EYCvvl9FnwRbAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:00.361332Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.00673","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d416ff0ca1f21f43db4b02ee58be8178d764df8f3293e9c50d0d53d7aea7840","sha256:7649e58c3c64f623f541deb53a2f08ecd79141fcf81bd0e317b45fcc14d27931"],"state_sha256":"4175fe429e0ffefec491e8e40ae943d0eb33c57881f36250497890f3c7a9f307"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oyqAm97YeL5CUllP+bgCoAvNFYw206KO/7fCUaIQs9gD4Zvw9NpQ7PddisoqwudcDipy3aMccu3tgByV3OnJCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T01:59:35.223771Z","bundle_sha256":"d81f689db7a165ccfd7b1846a63e3d5686ea7b045a6c9f310bae26e90591d830"}}